├── .github └── FUNDING.yml ├── .gitignore ├── LICENSE ├── LICENSE-MIT ├── LICENSES ├── README.md ├── alternative.html ├── config └── tailwind.css ├── css ├── hyperaudio-lite-editor.css ├── hyperaudio-lite-player.css ├── tailwind-dev.css └── tailwind-min.css ├── hyperaudio-template.html ├── images ├── favicon-16x16.png ├── favicon-32x32.png ├── icon-192x192.png ├── icon-512x512.png ├── maskable-icon-192x192.png └── poster.png ├── index.html ├── js ├── .prettierrc.json ├── audio-cut.js ├── caption-modified.js ├── hyperaudio-lite-editor-deepgram.js ├── hyperaudio-lite-editor-export.js ├── hyperaudio-lite-editor-storage.js ├── hyperaudio-lite-editor-whisper.js ├── hyperaudio-lite-extension.js ├── hyperaudio-lite.js ├── hyperaudio-push-notification.js └── whisper.worker.js ├── legacy.html ├── local.html ├── manifest.json ├── package-lock.json ├── package.json ├── postcss.config.js ├── serviceworker.js ├── tailwind.config.js ├── tailwind.md └── test └── test.mp3 /.github/FUNDING.yml: -------------------------------------------------------------------------------- 1 | # These are supported funding model platforms 2 | 3 | github: # Replace with up to 4 GitHub Sponsors-enabled usernames e.g., [user1, user2] 4 | patreon: Hyperaudio 5 | open_collective: # Replace with a single Open Collective username 6 | ko_fi: # Replace with a single Ko-fi username 7 | tidelift: # Replace with a single Tidelift platform-name/package-name e.g., npm/babel 8 | community_bridge: # Replace with a single Community Bridge project-name e.g., cloud-foundry 9 | liberapay: # Replace with a single Liberapay username 10 | issuehunt: # Replace with a single IssueHunt username 11 | otechie: # Replace with a single Otechie username 12 | lfx_crowdfunding: # Replace with a single LFX Crowdfunding project-name e.g., cloud-foundry 13 | custom: # Replace with up to 4 custom sponsorship URLs e.g., ['link1', 'link2'] 14 | -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- 1 | 2 | # Created by https://www.toptal.com/developers/gitignore/api/macos,node,linux 3 | # Edit at https://www.toptal.com/developers/gitignore?templates=macos,node,linux 4 | 5 | ### Linux ### 6 | *~ 7 | 8 | # temporary files which can be created if a process still has a handle open of a deleted file 9 | .fuse_hidden* 10 | 11 | # KDE directory preferences 12 | .directory 13 | 14 | # Linux trash folder which might appear on any partition or disk 15 | .Trash-* 16 | 17 | # .nfs files are created when an open file is removed but is still being accessed 18 | .nfs* 19 | 20 | ### macOS ### 21 | # General 22 | .DS_Store 23 | .AppleDouble 24 | .LSOverride 25 | 26 | # Icon must end with two \r 27 | Icon 28 | 29 | 30 | # Thumbnails 31 | ._* 32 | 33 | # Files that might appear in the root of a volume 34 | .DocumentRevisions-V100 35 | .fseventsd 36 | .Spotlight-V100 37 | .TemporaryItems 38 | .Trashes 39 | .VolumeIcon.icns 40 | .com.apple.timemachine.donotpresent 41 | 42 | # Directories potentially created on remote AFP share 43 | .AppleDB 44 | .AppleDesktop 45 | Network Trash Folder 46 | Temporary Items 47 | .apdisk 48 | 49 | ### Node ### 50 | # Logs 51 | logs 52 | *.log 53 | npm-debug.log* 54 | yarn-debug.log* 55 | yarn-error.log* 56 | lerna-debug.log* 57 | .pnpm-debug.log* 58 | 59 | # Diagnostic reports (https://nodejs.org/api/report.html) 60 | report.[0-9]*.[0-9]*.[0-9]*.[0-9]*.json 61 | 62 | # Runtime data 63 | pids 64 | *.pid 65 | *.seed 66 | *.pid.lock 67 | 68 | # Directory for instrumented libs generated by jscoverage/JSCover 69 | lib-cov 70 | 71 | # Coverage directory used by tools like istanbul 72 | coverage 73 | *.lcov 74 | 75 | # nyc test coverage 76 | .nyc_output 77 | 78 | # Grunt intermediate storage (https://gruntjs.com/creating-plugins#storing-task-files) 79 | .grunt 80 | 81 | # Bower dependency directory (https://bower.io/) 82 | bower_components 83 | 84 | # node-waf configuration 85 | .lock-wscript 86 | 87 | # Compiled binary addons (https://nodejs.org/api/addons.html) 88 | build/Release 89 | 90 | # Dependency directories 91 | node_modules/ 92 | jspm_packages/ 93 | 94 | # Snowpack dependency directory (https://snowpack.dev/) 95 | web_modules/ 96 | 97 | # TypeScript cache 98 | *.tsbuildinfo 99 | 100 | # Optional npm cache directory 101 | .npm 102 | 103 | # Optional eslint cache 104 | .eslintcache 105 | 106 | # Microbundle cache 107 | .rpt2_cache/ 108 | .rts2_cache_cjs/ 109 | .rts2_cache_es/ 110 | .rts2_cache_umd/ 111 | 112 | # Optional REPL history 113 | .node_repl_history 114 | 115 | # Output of 'npm pack' 116 | *.tgz 117 | 118 | # Yarn Integrity file 119 | .yarn-integrity 120 | 121 | # dotenv environment variables file 122 | .env 123 | .env.test 124 | .env.production 125 | 126 | # parcel-bundler cache (https://parceljs.org/) 127 | .cache 128 | .parcel-cache 129 | 130 | # Next.js build output 131 | .next 132 | out 133 | 134 | # Nuxt.js build / generate output 135 | .nuxt 136 | dist 137 | 138 | # Gatsby files 139 | .cache/ 140 | # Comment in the public line in if your project uses Gatsby and not Next.js 141 | # https://nextjs.org/blog/next-9-1#public-directory-support 142 | # public 143 | 144 | # vuepress build output 145 | .vuepress/dist 146 | 147 | # Serverless directories 148 | .serverless/ 149 | 150 | # FuseBox cache 151 | .fusebox/ 152 | 153 | # DynamoDB Local files 154 | .dynamodb/ 155 | 156 | # TernJS port file 157 | .tern-port 158 | 159 | # Stores VSCode versions used for testing VSCode extensions 160 | .vscode-test 161 | 162 | # yarn v2 163 | .yarn/cache 164 | .yarn/unplugged 165 | .yarn/build-state.yml 166 | .yarn/install-state.gz 167 | .pnp.* 168 | 169 | # End of https://www.toptal.com/developers/gitignore/api/macos,node,linux 170 | -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | GNU AFFERO GENERAL PUBLIC LICENSE 2 | Version 3, 19 November 2007 3 | 4 | Copyright (C) 2007 Free Software Foundation, Inc. 5 | Everyone is permitted to copy and distribute verbatim copies 6 | of this license document, but changing it is not allowed. 7 | 8 | Preamble 9 | 10 | The GNU Affero General Public License is a free, copyleft license for 11 | software and other kinds of works, specifically designed to ensure 12 | cooperation with the community in the case of network server software. 13 | 14 | The licenses for most software and other practical works are designed 15 | to take away your freedom to share and change the works. By contrast, 16 | our General Public Licenses are intended to guarantee your freedom to 17 | share and change all versions of a program--to make sure it remains free 18 | software for all its users. 19 | 20 | When we speak of free software, we are referring to freedom, not 21 | price. Our General Public Licenses are designed to make sure that you 22 | have the freedom to distribute copies of free software (and charge for 23 | them if you wish), that you receive source code or can get it if you 24 | want it, that you can change the software or use pieces of it in new 25 | free programs, and that you know you can do these things. 26 | 27 | Developers that use our General Public Licenses protect your rights 28 | with two steps: (1) assert copyright on the software, and (2) offer 29 | you this License which gives you legal permission to copy, distribute 30 | and/or modify the software. 31 | 32 | A secondary benefit of defending all users' freedom is that 33 | improvements made in alternate versions of the program, if they 34 | receive widespread use, become available for other developers to 35 | incorporate. Many developers of free software are heartened and 36 | encouraged by the resulting cooperation. However, in the case of 37 | software used on network servers, this result may fail to come about. 38 | The GNU General Public License permits making a modified version and 39 | letting the public access it on a server without ever releasing its 40 | source code to the public. 41 | 42 | The GNU Affero General Public License is designed specifically to 43 | ensure that, in such cases, the modified source code becomes available 44 | to the community. It requires the operator of a network server to 45 | provide the source code of the modified version running there to the 46 | users of that server. Therefore, public use of a modified version, on 47 | a publicly accessible server, gives the public access to the source 48 | code of the modified version. 49 | 50 | An older license, called the Affero General Public License and 51 | published by Affero, was designed to accomplish similar goals. This is 52 | a different license, not a version of the Affero GPL, but Affero has 53 | released a new version of the Affero GPL which permits relicensing under 54 | this license. 55 | 56 | The precise terms and conditions for copying, distribution and 57 | modification follow. 58 | 59 | TERMS AND CONDITIONS 60 | 61 | 0. Definitions. 62 | 63 | "This License" refers to version 3 of the GNU Affero General Public License. 64 | 65 | "Copyright" also means copyright-like laws that apply to other kinds of 66 | works, such as semiconductor masks. 67 | 68 | "The Program" refers to any copyrightable work licensed under this 69 | License. Each licensee is addressed as "you". "Licensees" and 70 | "recipients" may be individuals or organizations. 71 | 72 | To "modify" a work means to copy from or adapt all or part of the work 73 | in a fashion requiring copyright permission, other than the making of an 74 | exact copy. The resulting work is called a "modified version" of the 75 | earlier work or a work "based on" the earlier work. 76 | 77 | A "covered work" means either the unmodified Program or a work based 78 | on the Program. 79 | 80 | To "propagate" a work means to do anything with it that, without 81 | permission, would make you directly or secondarily liable for 82 | infringement under applicable copyright law, except executing it on a 83 | computer or modifying a private copy. Propagation includes copying, 84 | distribution (with or without modification), making available to the 85 | public, and in some countries other activities as well. 86 | 87 | To "convey" a work means any kind of propagation that enables other 88 | parties to make or receive copies. Mere interaction with a user through 89 | a computer network, with no transfer of a copy, is not conveying. 90 | 91 | An interactive user interface displays "Appropriate Legal Notices" 92 | to the extent that it includes a convenient and prominently visible 93 | feature that (1) displays an appropriate copyright notice, and (2) 94 | tells the user that there is no warranty for the work (except to the 95 | extent that warranties are provided), that licensees may convey the 96 | work under this License, and how to view a copy of this License. If 97 | the interface presents a list of user commands or options, such as a 98 | menu, a prominent item in the list meets this criterion. 99 | 100 | 1. Source Code. 101 | 102 | The "source code" for a work means the preferred form of the work 103 | for making modifications to it. "Object code" means any non-source 104 | form of a work. 105 | 106 | A "Standard Interface" means an interface that either is an official 107 | standard defined by a recognized standards body, or, in the case of 108 | interfaces specified for a particular programming language, one that 109 | is widely used among developers working in that language. 110 | 111 | The "System Libraries" of an executable work include anything, other 112 | than the work as a whole, that (a) is included in the normal form of 113 | packaging a Major Component, but which is not part of that Major 114 | Component, and (b) serves only to enable use of the work with that 115 | Major Component, or to implement a Standard Interface for which an 116 | implementation is available to the public in source code form. A 117 | "Major Component", in this context, means a major essential component 118 | (kernel, window system, and so on) of the specific operating system 119 | (if any) on which the executable work runs, or a compiler used to 120 | produce the work, or an object code interpreter used to run it. 121 | 122 | The "Corresponding Source" for a work in object code form means all 123 | the source code needed to generate, install, and (for an executable 124 | work) run the object code and to modify the work, including scripts to 125 | control those activities. However, it does not include the work's 126 | System Libraries, or general-purpose tools or generally available free 127 | programs which are used unmodified in performing those activities but 128 | which are not part of the work. For example, Corresponding Source 129 | includes interface definition files associated with source files for 130 | the work, and the source code for shared libraries and dynamically 131 | linked subprograms that the work is specifically designed to require, 132 | such as by intimate data communication or control flow between those 133 | subprograms and other parts of the work. 134 | 135 | The Corresponding Source need not include anything that users 136 | can regenerate automatically from other parts of the Corresponding 137 | Source. 138 | 139 | The Corresponding Source for a work in source code form is that 140 | same work. 141 | 142 | 2. Basic Permissions. 143 | 144 | All rights granted under this License are granted for the term of 145 | copyright on the Program, and are irrevocable provided the stated 146 | conditions are met. This License explicitly affirms your unlimited 147 | permission to run the unmodified Program. The output from running a 148 | covered work is covered by this License only if the output, given its 149 | content, constitutes a covered work. This License acknowledges your 150 | rights of fair use or other equivalent, as provided by copyright law. 151 | 152 | You may make, run and propagate covered works that you do not 153 | convey, without conditions so long as your license otherwise remains 154 | in force. You may convey covered works to others for the sole purpose 155 | of having them make modifications exclusively for you, or provide you 156 | with facilities for running those works, provided that you comply with 157 | the terms of this License in conveying all material for which you do 158 | not control copyright. Those thus making or running the covered works 159 | for you must do so exclusively on your behalf, under your direction 160 | and control, on terms that prohibit them from making any copies of 161 | your copyrighted material outside their relationship with you. 162 | 163 | Conveying under any other circumstances is permitted solely under 164 | the conditions stated below. Sublicensing is not allowed; section 10 165 | makes it unnecessary. 166 | 167 | 3. Protecting Users' Legal Rights From Anti-Circumvention Law. 168 | 169 | No covered work shall be deemed part of an effective technological 170 | measure under any applicable law fulfilling obligations under article 171 | 11 of the WIPO copyright treaty adopted on 20 December 1996, or 172 | similar laws prohibiting or restricting circumvention of such 173 | measures. 174 | 175 | When you convey a covered work, you waive any legal power to forbid 176 | circumvention of technological measures to the extent such circumvention 177 | is effected by exercising rights under this License with respect to 178 | the covered work, and you disclaim any intention to limit operation or 179 | modification of the work as a means of enforcing, against the work's 180 | users, your or third parties' legal rights to forbid circumvention of 181 | technological measures. 182 | 183 | 4. Conveying Verbatim Copies. 184 | 185 | You may convey verbatim copies of the Program's source code as you 186 | receive it, in any medium, provided that you conspicuously and 187 | appropriately publish on each copy an appropriate copyright notice; 188 | keep intact all notices stating that this License and any 189 | non-permissive terms added in accord with section 7 apply to the code; 190 | keep intact all notices of the absence of any warranty; and give all 191 | recipients a copy of this License along with the Program. 192 | 193 | You may charge any price or no price for each copy that you convey, 194 | and you may offer support or warranty protection for a fee. 195 | 196 | 5. Conveying Modified Source Versions. 197 | 198 | You may convey a work based on the Program, or the modifications to 199 | produce it from the Program, in the form of source code under the 200 | terms of section 4, provided that you also meet all of these conditions: 201 | 202 | a) The work must carry prominent notices stating that you modified 203 | it, and giving a relevant date. 204 | 205 | b) The work must carry prominent notices stating that it is 206 | released under this License and any conditions added under section 207 | 7. This requirement modifies the requirement in section 4 to 208 | "keep intact all notices". 209 | 210 | c) You must license the entire work, as a whole, under this 211 | License to anyone who comes into possession of a copy. This 212 | License will therefore apply, along with any applicable section 7 213 | additional terms, to the whole of the work, and all its parts, 214 | regardless of how they are packaged. This License gives no 215 | permission to license the work in any other way, but it does not 216 | invalidate such permission if you have separately received it. 217 | 218 | d) If the work has interactive user interfaces, each must display 219 | Appropriate Legal Notices; however, if the Program has interactive 220 | interfaces that do not display Appropriate Legal Notices, your 221 | work need not make them do so. 222 | 223 | A compilation of a covered work with other separate and independent 224 | works, which are not by their nature extensions of the covered work, 225 | and which are not combined with it such as to form a larger program, 226 | in or on a volume of a storage or distribution medium, is called an 227 | "aggregate" if the compilation and its resulting copyright are not 228 | used to limit the access or legal rights of the compilation's users 229 | beyond what the individual works permit. Inclusion of a covered work 230 | in an aggregate does not cause this License to apply to the other 231 | parts of the aggregate. 232 | 233 | 6. Conveying Non-Source Forms. 234 | 235 | You may convey a covered work in object code form under the terms 236 | of sections 4 and 5, provided that you also convey the 237 | machine-readable Corresponding Source under the terms of this License, 238 | in one of these ways: 239 | 240 | a) Convey the object code in, or embodied in, a physical product 241 | (including a physical distribution medium), accompanied by the 242 | Corresponding Source fixed on a durable physical medium 243 | customarily used for software interchange. 244 | 245 | b) Convey the object code in, or embodied in, a physical product 246 | (including a physical distribution medium), accompanied by a 247 | written offer, valid for at least three years and valid for as 248 | long as you offer spare parts or customer support for that product 249 | model, to give anyone who possesses the object code either (1) a 250 | copy of the Corresponding Source for all the software in the 251 | product that is covered by this License, on a durable physical 252 | medium customarily used for software interchange, for a price no 253 | more than your reasonable cost of physically performing this 254 | conveying of source, or (2) access to copy the 255 | Corresponding Source from a network server at no charge. 256 | 257 | c) Convey individual copies of the object code with a copy of the 258 | written offer to provide the Corresponding Source. This 259 | alternative is allowed only occasionally and noncommercially, and 260 | only if you received the object code with such an offer, in accord 261 | with subsection 6b. 262 | 263 | d) Convey the object code by offering access from a designated 264 | place (gratis or for a charge), and offer equivalent access to the 265 | Corresponding Source in the same way through the same place at no 266 | further charge. You need not require recipients to copy the 267 | Corresponding Source along with the object code. If the place to 268 | copy the object code is a network server, the Corresponding Source 269 | may be on a different server (operated by you or a third party) 270 | that supports equivalent copying facilities, provided you maintain 271 | clear directions next to the object code saying where to find the 272 | Corresponding Source. Regardless of what server hosts the 273 | Corresponding Source, you remain obligated to ensure that it is 274 | available for as long as needed to satisfy these requirements. 275 | 276 | e) Convey the object code using peer-to-peer transmission, provided 277 | you inform other peers where the object code and Corresponding 278 | Source of the work are being offered to the general public at no 279 | charge under subsection 6d. 280 | 281 | A separable portion of the object code, whose source code is excluded 282 | from the Corresponding Source as a System Library, need not be 283 | included in conveying the object code work. 284 | 285 | A "User Product" is either (1) a "consumer product", which means any 286 | tangible personal property which is normally used for personal, family, 287 | or household purposes, or (2) anything designed or sold for incorporation 288 | into a dwelling. In determining whether a product is a consumer product, 289 | doubtful cases shall be resolved in favor of coverage. For a particular 290 | product received by a particular user, "normally used" refers to a 291 | typical or common use of that class of product, regardless of the status 292 | of the particular user or of the way in which the particular user 293 | actually uses, or expects or is expected to use, the product. A product 294 | is a consumer product regardless of whether the product has substantial 295 | commercial, industrial or non-consumer uses, unless such uses represent 296 | the only significant mode of use of the product. 297 | 298 | "Installation Information" for a User Product means any methods, 299 | procedures, authorization keys, or other information required to install 300 | and execute modified versions of a covered work in that User Product from 301 | a modified version of its Corresponding Source. The information must 302 | suffice to ensure that the continued functioning of the modified object 303 | code is in no case prevented or interfered with solely because 304 | modification has been made. 305 | 306 | If you convey an object code work under this section in, or with, or 307 | specifically for use in, a User Product, and the conveying occurs as 308 | part of a transaction in which the right of possession and use of the 309 | User Product is transferred to the recipient in perpetuity or for a 310 | fixed term (regardless of how the transaction is characterized), the 311 | Corresponding Source conveyed under this section must be accompanied 312 | by the Installation Information. But this requirement does not apply 313 | if neither you nor any third party retains the ability to install 314 | modified object code on the User Product (for example, the work has 315 | been installed in ROM). 316 | 317 | The requirement to provide Installation Information does not include a 318 | requirement to continue to provide support service, warranty, or updates 319 | for a work that has been modified or installed by the recipient, or for 320 | the User Product in which it has been modified or installed. Access to a 321 | network may be denied when the modification itself materially and 322 | adversely affects the operation of the network or violates the rules and 323 | protocols for communication across the network. 324 | 325 | Corresponding Source conveyed, and Installation Information provided, 326 | in accord with this section must be in a format that is publicly 327 | documented (and with an implementation available to the public in 328 | source code form), and must require no special password or key for 329 | unpacking, reading or copying. 330 | 331 | 7. Additional Terms. 332 | 333 | "Additional permissions" are terms that supplement the terms of this 334 | License by making exceptions from one or more of its conditions. 335 | Additional permissions that are applicable to the entire Program shall 336 | be treated as though they were included in this License, to the extent 337 | that they are valid under applicable law. If additional permissions 338 | apply only to part of the Program, that part may be used separately 339 | under those permissions, but the entire Program remains governed by 340 | this License without regard to the additional permissions. 341 | 342 | When you convey a copy of a covered work, you may at your option 343 | remove any additional permissions from that copy, or from any part of 344 | it. (Additional permissions may be written to require their own 345 | removal in certain cases when you modify the work.) You may place 346 | additional permissions on material, added by you to a covered work, 347 | for which you have or can give appropriate copyright permission. 348 | 349 | Notwithstanding any other provision of this License, for material you 350 | add to a covered work, you may (if authorized by the copyright holders of 351 | that material) supplement the terms of this License with terms: 352 | 353 | a) Disclaiming warranty or limiting liability differently from the 354 | terms of sections 15 and 16 of this License; or 355 | 356 | b) Requiring preservation of specified reasonable legal notices or 357 | author attributions in that material or in the Appropriate Legal 358 | Notices displayed by works containing it; or 359 | 360 | c) Prohibiting misrepresentation of the origin of that material, or 361 | requiring that modified versions of such material be marked in 362 | reasonable ways as different from the original version; or 363 | 364 | d) Limiting the use for publicity purposes of names of licensors or 365 | authors of the material; or 366 | 367 | e) Declining to grant rights under trademark law for use of some 368 | trade names, trademarks, or service marks; or 369 | 370 | f) Requiring indemnification of licensors and authors of that 371 | material by anyone who conveys the material (or modified versions of 372 | it) with contractual assumptions of liability to the recipient, for 373 | any liability that these contractual assumptions directly impose on 374 | those licensors and authors. 375 | 376 | All other non-permissive additional terms are considered "further 377 | restrictions" within the meaning of section 10. If the Program as you 378 | received it, or any part of it, contains a notice stating that it is 379 | governed by this License along with a term that is a further 380 | restriction, you may remove that term. If a license document contains 381 | a further restriction but permits relicensing or conveying under this 382 | License, you may add to a covered work material governed by the terms 383 | of that license document, provided that the further restriction does 384 | not survive such relicensing or conveying. 385 | 386 | If you add terms to a covered work in accord with this section, you 387 | must place, in the relevant source files, a statement of the 388 | additional terms that apply to those files, or a notice indicating 389 | where to find the applicable terms. 390 | 391 | Additional terms, permissive or non-permissive, may be stated in the 392 | form of a separately written license, or stated as exceptions; 393 | the above requirements apply either way. 394 | 395 | 8. Termination. 396 | 397 | You may not propagate or modify a covered work except as expressly 398 | provided under this License. Any attempt otherwise to propagate or 399 | modify it is void, and will automatically terminate your rights under 400 | this License (including any patent licenses granted under the third 401 | paragraph of section 11). 402 | 403 | However, if you cease all violation of this License, then your 404 | license from a particular copyright holder is reinstated (a) 405 | provisionally, unless and until the copyright holder explicitly and 406 | finally terminates your license, and (b) permanently, if the copyright 407 | holder fails to notify you of the violation by some reasonable means 408 | prior to 60 days after the cessation. 409 | 410 | Moreover, your license from a particular copyright holder is 411 | reinstated permanently if the copyright holder notifies you of the 412 | violation by some reasonable means, this is the first time you have 413 | received notice of violation of this License (for any work) from that 414 | copyright holder, and you cure the violation prior to 30 days after 415 | your receipt of the notice. 416 | 417 | Termination of your rights under this section does not terminate the 418 | licenses of parties who have received copies or rights from you under 419 | this License. If your rights have been terminated and not permanently 420 | reinstated, you do not qualify to receive new licenses for the same 421 | material under section 10. 422 | 423 | 9. Acceptance Not Required for Having Copies. 424 | 425 | You are not required to accept this License in order to receive or 426 | run a copy of the Program. Ancillary propagation of a covered work 427 | occurring solely as a consequence of using peer-to-peer transmission 428 | to receive a copy likewise does not require acceptance. However, 429 | nothing other than this License grants you permission to propagate or 430 | modify any covered work. These actions infringe copyright if you do 431 | not accept this License. Therefore, by modifying or propagating a 432 | covered work, you indicate your acceptance of this License to do so. 433 | 434 | 10. Automatic Licensing of Downstream Recipients. 435 | 436 | Each time you convey a covered work, the recipient automatically 437 | receives a license from the original licensors, to run, modify and 438 | propagate that work, subject to this License. You are not responsible 439 | for enforcing compliance by third parties with this License. 440 | 441 | An "entity transaction" is a transaction transferring control of an 442 | organization, or substantially all assets of one, or subdividing an 443 | organization, or merging organizations. If propagation of a covered 444 | work results from an entity transaction, each party to that 445 | transaction who receives a copy of the work also receives whatever 446 | licenses to the work the party's predecessor in interest had or could 447 | give under the previous paragraph, plus a right to possession of the 448 | Corresponding Source of the work from the predecessor in interest, if 449 | the predecessor has it or can get it with reasonable efforts. 450 | 451 | You may not impose any further restrictions on the exercise of the 452 | rights granted or affirmed under this License. For example, you may 453 | not impose a license fee, royalty, or other charge for exercise of 454 | rights granted under this License, and you may not initiate litigation 455 | (including a cross-claim or counterclaim in a lawsuit) alleging that 456 | any patent claim is infringed by making, using, selling, offering for 457 | sale, or importing the Program or any portion of it. 458 | 459 | 11. Patents. 460 | 461 | A "contributor" is a copyright holder who authorizes use under this 462 | License of the Program or a work on which the Program is based. The 463 | work thus licensed is called the contributor's "contributor version". 464 | 465 | A contributor's "essential patent claims" are all patent claims 466 | owned or controlled by the contributor, whether already acquired or 467 | hereafter acquired, that would be infringed by some manner, permitted 468 | by this License, of making, using, or selling its contributor version, 469 | but do not include claims that would be infringed only as a 470 | consequence of further modification of the contributor version. For 471 | purposes of this definition, "control" includes the right to grant 472 | patent sublicenses in a manner consistent with the requirements of 473 | this License. 474 | 475 | Each contributor grants you a non-exclusive, worldwide, royalty-free 476 | patent license under the contributor's essential patent claims, to 477 | make, use, sell, offer for sale, import and otherwise run, modify and 478 | propagate the contents of its contributor version. 479 | 480 | In the following three paragraphs, a "patent license" is any express 481 | agreement or commitment, however denominated, not to enforce a patent 482 | (such as an express permission to practice a patent or covenant not to 483 | sue for patent infringement). To "grant" such a patent license to a 484 | party means to make such an agreement or commitment not to enforce a 485 | patent against the party. 486 | 487 | If you convey a covered work, knowingly relying on a patent license, 488 | and the Corresponding Source of the work is not available for anyone 489 | to copy, free of charge and under the terms of this License, through a 490 | publicly available network server or other readily accessible means, 491 | then you must either (1) cause the Corresponding Source to be so 492 | available, or (2) arrange to deprive yourself of the benefit of the 493 | patent license for this particular work, or (3) arrange, in a manner 494 | consistent with the requirements of this License, to extend the patent 495 | license to downstream recipients. "Knowingly relying" means you have 496 | actual knowledge that, but for the patent license, your conveying the 497 | covered work in a country, or your recipient's use of the covered work 498 | in a country, would infringe one or more identifiable patents in that 499 | country that you have reason to believe are valid. 500 | 501 | If, pursuant to or in connection with a single transaction or 502 | arrangement, you convey, or propagate by procuring conveyance of, a 503 | covered work, and grant a patent license to some of the parties 504 | receiving the covered work authorizing them to use, propagate, modify 505 | or convey a specific copy of the covered work, then the patent license 506 | you grant is automatically extended to all recipients of the covered 507 | work and works based on it. 508 | 509 | A patent license is "discriminatory" if it does not include within 510 | the scope of its coverage, prohibits the exercise of, or is 511 | conditioned on the non-exercise of one or more of the rights that are 512 | specifically granted under this License. You may not convey a covered 513 | work if you are a party to an arrangement with a third party that is 514 | in the business of distributing software, under which you make payment 515 | to the third party based on the extent of your activity of conveying 516 | the work, and under which the third party grants, to any of the 517 | parties who would receive the covered work from you, a discriminatory 518 | patent license (a) in connection with copies of the covered work 519 | conveyed by you (or copies made from those copies), or (b) primarily 520 | for and in connection with specific products or compilations that 521 | contain the covered work, unless you entered into that arrangement, 522 | or that patent license was granted, prior to 28 March 2007. 523 | 524 | Nothing in this License shall be construed as excluding or limiting 525 | any implied license or other defenses to infringement that may 526 | otherwise be available to you under applicable patent law. 527 | 528 | 12. No Surrender of Others' Freedom. 529 | 530 | If conditions are imposed on you (whether by court order, agreement or 531 | otherwise) that contradict the conditions of this License, they do not 532 | excuse you from the conditions of this License. If you cannot convey a 533 | covered work so as to satisfy simultaneously your obligations under this 534 | License and any other pertinent obligations, then as a consequence you may 535 | not convey it at all. For example, if you agree to terms that obligate you 536 | to collect a royalty for further conveying from those to whom you convey 537 | the Program, the only way you could satisfy both those terms and this 538 | License would be to refrain entirely from conveying the Program. 539 | 540 | 13. Remote Network Interaction; Use with the GNU General Public License. 541 | 542 | Notwithstanding any other provision of this License, if you modify the 543 | Program, your modified version must prominently offer all users 544 | interacting with it remotely through a computer network (if your version 545 | supports such interaction) an opportunity to receive the Corresponding 546 | Source of your version by providing access to the Corresponding Source 547 | from a network server at no charge, through some standard or customary 548 | means of facilitating copying of software. This Corresponding Source 549 | shall include the Corresponding Source for any work covered by version 3 550 | of the GNU General Public License that is incorporated pursuant to the 551 | following paragraph. 552 | 553 | Notwithstanding any other provision of this License, you have 554 | permission to link or combine any covered work with a work licensed 555 | under version 3 of the GNU General Public License into a single 556 | combined work, and to convey the resulting work. The terms of this 557 | License will continue to apply to the part which is the covered work, 558 | but the work with which it is combined will remain governed by version 559 | 3 of the GNU General Public License. 560 | 561 | 14. Revised Versions of this License. 562 | 563 | The Free Software Foundation may publish revised and/or new versions of 564 | the GNU Affero General Public License from time to time. Such new versions 565 | will be similar in spirit to the present version, but may differ in detail to 566 | address new problems or concerns. 567 | 568 | Each version is given a distinguishing version number. If the 569 | Program specifies that a certain numbered version of the GNU Affero General 570 | Public License "or any later version" applies to it, you have the 571 | option of following the terms and conditions either of that numbered 572 | version or of any later version published by the Free Software 573 | Foundation. If the Program does not specify a version number of the 574 | GNU Affero General Public License, you may choose any version ever published 575 | by the Free Software Foundation. 576 | 577 | If the Program specifies that a proxy can decide which future 578 | versions of the GNU Affero General Public License can be used, that proxy's 579 | public statement of acceptance of a version permanently authorizes you 580 | to choose that version for the Program. 581 | 582 | Later license versions may give you additional or different 583 | permissions. However, no additional obligations are imposed on any 584 | author or copyright holder as a result of your choosing to follow a 585 | later version. 586 | 587 | 15. Disclaimer of Warranty. 588 | 589 | THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY 590 | APPLICABLE LAW. EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT 591 | HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY 592 | OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, 593 | THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR 594 | PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM 595 | IS WITH YOU. SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF 596 | ALL NECESSARY SERVICING, REPAIR OR CORRECTION. 597 | 598 | 16. Limitation of Liability. 599 | 600 | IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING 601 | WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS 602 | THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY 603 | GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE 604 | USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF 605 | DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD 606 | PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS), 607 | EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF 608 | SUCH DAMAGES. 609 | 610 | 17. Interpretation of Sections 15 and 16. 611 | 612 | If the disclaimer of warranty and limitation of liability provided 613 | above cannot be given local legal effect according to their terms, 614 | reviewing courts shall apply local law that most closely approximates 615 | an absolute waiver of all civil liability in connection with the 616 | Program, unless a warranty or assumption of liability accompanies a 617 | copy of the Program in return for a fee. 618 | 619 | END OF TERMS AND CONDITIONS 620 | 621 | How to Apply These Terms to Your New Programs 622 | 623 | If you develop a new program, and you want it to be of the greatest 624 | possible use to the public, the best way to achieve this is to make it 625 | free software which everyone can redistribute and change under these terms. 626 | 627 | To do so, attach the following notices to the program. It is safest 628 | to attach them to the start of each source file to most effectively 629 | state the exclusion of warranty; and each file should have at least 630 | the "copyright" line and a pointer to where the full notice is found. 631 | 632 | 633 | Copyright (C) 634 | 635 | This program is free software: you can redistribute it and/or modify 636 | it under the terms of the GNU Affero General Public License as published 637 | by the Free Software Foundation, either version 3 of the License, or 638 | (at your option) any later version. 639 | 640 | This program is distributed in the hope that it will be useful, 641 | but WITHOUT ANY WARRANTY; without even the implied warranty of 642 | MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the 643 | GNU Affero General Public License for more details. 644 | 645 | You should have received a copy of the GNU Affero General Public License 646 | along with this program. If not, see . 647 | 648 | Also add information on how to contact you by electronic and paper mail. 649 | 650 | If your software can interact with users remotely through a computer 651 | network, you should also make sure that it provides a way for users to 652 | get its source. For example, if your program is a web application, its 653 | interface could display a "Source" link that leads users to an archive 654 | of the code. There are many ways you could offer source, and different 655 | solutions will be better for different programs; see section 13 for the 656 | specific requirements. 657 | 658 | You should also get your employer (if you work as a programmer) or school, 659 | if any, to sign a "copyright disclaimer" for the program, if necessary. 660 | For more information on this, and how to apply and follow the GNU AGPL, see 661 | . 662 | -------------------------------------------------------------------------------- /LICENSE-MIT: -------------------------------------------------------------------------------- 1 | MIT License 2 | 3 | Copyright (c) 2025 The Hyperaudio Project 4 | 5 | Permission is hereby granted, free of charge, to any person obtaining a copy 6 | of this software and associated documentation files (the "Software"), to deal 7 | in the Software without restriction, including without limitation the rights 8 | to use, copy, modify, merge, publish, distribute, sublicense, and/or sell 9 | copies of the Software, and to permit persons to whom the Software is 10 | furnished to do so, subject to the following conditions: 11 | 12 | The above copyright notice and this permission notice shall be included in all 13 | copies or substantial portions of the Software. 14 | 15 | THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 16 | IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 17 | FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE 18 | AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 19 | LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, 20 | OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE 21 | SOFTWARE. 22 | -------------------------------------------------------------------------------- /LICENSES: -------------------------------------------------------------------------------- 1 | An Important Note About Licensing 2 | --------------------------------- 3 | 4 | Our default License is the AGPL3.0 License. 5 | 6 | For commerical use please refer to our main AGPL3.0 License (https://github.com/hyperaudio/hyperaudio-lite-editor/blob/main/LICENSE) or contact us for enquiries about commercial licensing. 7 | 8 | The MIT license applies to non-commercial entities. 9 | 10 | For any enquiries please contact mark@hyperaud.io 11 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | 2 | # Hyperaudio Lite Editor 3 | A lightweight transcript editor for editing and correcting machine generated transcripts. 4 | 5 | Super Lightweight :snowflake: 6 | Lightning Fast :zap: 7 | Accessible :couple_with_heart: 8 | Installable :computer: 9 | Portable :iphone: 10 | 11 | ### Formats 12 | 13 | Export your transcript as text, interactive transcript, captions and subtitles. 14 | 15 | ### Try it out! 16 | 17 | [Demo (now with localStorage and installable as a Progressive Web App)](https://hyperaudio.github.io/hyperaudio-lite-editor/index.html) 18 | 19 | [Screen capture of Hyperaudio Lite Editor](https://hyperaudio.github.io/hyperaudio-lite-editor/index.html) 20 | 21 | 22 | ### How to Use 23 | 24 | Edit in the usual way – add punctuation, create and merge paragraphs etc. Place speaker names in square brackets ie [Maria]. It's recommended that in order to maintain word timings you don't paste large blocks of text. Double-click on words to set the playhead at that point. 25 | 26 | ### Lightweight, Performant and Installable 27 | 28 | We score very highly on Google Chrome's Lighthouse audit tool 29 | 30 | Chrome Lighthouse showing maximum accessibility, performance and best practice scores 31 | 32 | Created as a Progressive Web App, you can install on your desktop or mobile home screen. 33 | 34 | 35 | ### Licensing 36 | 37 | `Hyperaudio Lite Editor`'s source code is provided under a **triple license model**. 38 | 39 | #### Open source license 40 | 41 | If you are creating an open source application under a license compatible with the GNU Affero GPL license v3, you may use `Hyperaudio Lite Editor` for free under the terms of the [AGPL-3.0](./LICENSE). This is the deafult license for `Hyperaudio Lite Editor`. 42 | 43 | #### Non-commercial use 44 | 45 | If you are a non-commerical / not-for-profit entity or organisation and wish to to use this software for non-commercial please contact [mark@hyperaud.io](mailto:mark@hyperaud.io) to use `Hyperaudio Lite Editor` for free under the terms of the [MIT License](/.LICENSE-MIT) 46 | 47 | #### Commercial license 48 | 49 | If you'd like to use `Hyperaudio Lite Editor` to develop commercial sites, tools, and applications, the Commercial License is the appropriate license. With this option, your source code is kept proprietary. To enquire about a `Hyperaudio Lite Editor` Commercial License please contact [mark@hyperaud.io](mailto:mark@hyperaud.io). 50 | 51 | ### Support 52 | 53 | Please support The Hyperaudio Project by donating to our [Patreon account](https://patreon.com/hyperaudio). 54 | -------------------------------------------------------------------------------- /alternative.html: -------------------------------------------------------------------------------- 1 | 2 | 3 | 14 | 15 | 16 |
17 |

18 | 19 |

20 |

The alternative version is now the default version, which can be found here.

21 |
22 | 23 | 24 | -------------------------------------------------------------------------------- /config/tailwind.css: -------------------------------------------------------------------------------- 1 | @tailwind base; 2 | @tailwind components; 3 | @tailwind utilities; 4 | -------------------------------------------------------------------------------- /css/hyperaudio-lite-editor.css: -------------------------------------------------------------------------------- 1 | body { 2 | font-family: system-ui,-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,Oxygen,Ubuntu,Cantarell,'Fira Sans','Droid Sans','Helvetica Neue',sans-serif; 3 | line-height: 1.8; 4 | } 5 | 6 | input, output, select, button, textarea { 7 | display: inline-block; 8 | padding: 8px; 9 | margin-bottom:8px; 10 | margin-right:4px; 11 | font-size: 12pt; 12 | border-radius: 3px; 13 | border: 1px solid #ddd; 14 | } 15 | 16 | video { 17 | border-radius: 3px; 18 | } 19 | 20 | button, input[type="submit"], input[type="file"] { 21 | border: 1px solid #ccc; 22 | background-color: #ddd; 23 | } 24 | 25 | button:hover, input[type="submit"]:hover, input[type="file"]:hover { 26 | border: 1px solid #999; 27 | background-color: #ccc; 28 | cursor: pointer; 29 | } 30 | 31 | input[type="number"] { 32 | width: 42px; 33 | } 34 | 35 | #search { 36 | width: 230px; 37 | margin-right: 4px; 38 | } 39 | 40 | #pbr-holder { 41 | padding-top: 20px; 42 | } 43 | 44 | .top-bar-container { 45 | /*display: flex;*/ 46 | display: grid; 47 | grid-template-columns: 1fr 1fr 1fr; 48 | } 49 | 50 | dialog::backdrop { 51 | backdrop-filter: blur(1px); 52 | } 53 | 54 | .vertically-centre { 55 | padding-top: 40%; 56 | } 57 | 58 | .hyperaudio-transcript { 59 | font-size: 13pt; 60 | } 61 | 62 | /* for accessibility */ 63 | .hidden-label-holder { 64 | height:0; 65 | opacity: 0; 66 | } 67 | 68 | /* former inline styles */ 69 | .transcript-holder { 70 | display: flex; 71 | justify-content: center; 72 | background-color: #ffffff; 73 | overflow-y:scroll; 74 | position: absolute; 75 | top: 70px; 76 | left: 400px; 77 | right: 0; 78 | bottom: 0; 79 | transition: left 0.5s ease; 80 | } 81 | 82 | .hyperaudio-transcript { 83 | position: absolute; 84 | top: 10px; 85 | bottom: 0px; 86 | background-color: #ffffff; 87 | padding-top: 48px; 88 | width: 520px; 89 | outline: none; 90 | } 91 | 92 | #file-dropdown-mobile, #file-dropdown-symbol-mobile, #transcribe-label-mobile { 93 | display: none; 94 | } 95 | 96 | @media screen and (max-width: 1120px) { 97 | #file-dropdown-symbol-mobile { 98 | display: block; 99 | } 100 | 101 | #file-dropdown-text, #file-dropdown-symbol { 102 | display: none; 103 | } 104 | 105 | .hyperaudio-transcript { 106 | position: relative; 107 | width: 520px; 108 | } 109 | 110 | .transcript-holder { 111 | display: block; 112 | justify-content: center; 113 | background-color: #ffffff; 114 | overflow-y:scroll; 115 | top: 0; 116 | right: 0; 117 | bottom: 0; 118 | width: 100%; 119 | padding: 8px; 120 | } 121 | 122 | #transcribe-label { 123 | display: none; 124 | } 125 | 126 | #transcribe-label-mobile { 127 | display: block; 128 | } 129 | 130 | 131 | } 132 | 133 | @media screen and (max-width: 480px) { 134 | 135 | .hyperaudio-transcript { 136 | top: 40px; 137 | bottom: 0px; 138 | background-color: #ffffff; 139 | padding-top: 48px; 140 | width: 100%; 141 | outline: none; 142 | } 143 | 144 | .transcript-holder { 145 | left: 0px; 146 | } 147 | 148 | .side-panel, #transcribe-label { 149 | display: none; 150 | } 151 | 152 | .main-panel { 153 | left: 0; 154 | } 155 | 156 | .holder { 157 | left: 0; 158 | } 159 | 160 | #search-box, #sidebar-toggle, #regenerate-icon{ 161 | display: none; 162 | } 163 | 164 | /*.navbar-start { 165 | width: 36%; 166 | }*/ 167 | 168 | .modal-box { 169 | width:300px; 170 | } 171 | 172 | .caption-row input.line1, .caption-row input.line2 { 173 | width: 24ch; 174 | } 175 | 176 | .caption-row input.start, .caption-row input.end { 177 | width: 12ch; 178 | } 179 | 180 | 181 | } 182 | -------------------------------------------------------------------------------- /css/hyperaudio-lite-player.css: -------------------------------------------------------------------------------- 1 | /*! (C) The Hyperaudio Project. MIT @license: en.wikipedia.org/wiki/MIT_License. */ 2 | /* Updated for Version 2.1 */ 3 | 4 | .hyperaudio-transcript .strikethrough { 5 | text-decoration: line-through; 6 | } 7 | 8 | .hyperaudio-transcript .annotation, .hyperaudio-transcript .parannotation{ 9 | opacity: 0.7; 10 | } 11 | 12 | .hyperaudio-transcript .highlight { 13 | background-color: yellow; 14 | } 15 | 16 | .hyperaudio-transcript .highlight.active { 17 | background-color: lightGreen; 18 | } 19 | 20 | .hyperaudio-transcript header { 21 | font-size: 200%; 22 | } 23 | 24 | /*.hyperaudio-transcript a { 25 | cursor: pointer; 26 | color: #000; 27 | }*/ 28 | 29 | 30 | .hyperaudio-transcript a, a.link { 31 | border: 0px; 32 | } 33 | 34 | .hyperaudio-transcript .read { 35 | color: #000; 36 | } 37 | 38 | .hyperaudio-transcript .active > .active { 39 | color: #000; 40 | } 41 | 42 | .hyperaudio-transcript .unread { 43 | color: #666; 44 | } 45 | 46 | .hyperaudio-transcript .search-match { 47 | background-color: pink; 48 | } 49 | 50 | .hyperaudio-transcript .share-match { 51 | background-color: #66ffad; 52 | } 53 | 54 | .hyperaudio-transcript sub:before { 55 | content: '\231C'; 56 | } 57 | 58 | .hyperaudio-transcript sub.highlight-duration:before { 59 | content: '\231D'; 60 | } 61 | 62 | .hyperaudio-transcript h5 { 63 | font-size: 130%; 64 | } 65 | 66 | [data-m] { 67 | cursor: pointer; 68 | } 69 | 70 | body { 71 | font-family: "Palatino Linotype", "Book Antiqua", Palatino, serif; 72 | line-height: 1.5; 73 | } 74 | 75 | .speaker { 76 | font-weight: bold; 77 | } 78 | -------------------------------------------------------------------------------- /hyperaudio-template.html: -------------------------------------------------------------------------------- 1 | 2 | 3 | 4 | 5 | Hyperaudio – Interactive Transcript 6 | 7 | 8 | 9 | 10 | 11 | 12 | 15 | 16 |
17 | {hypertranscript} 18 |
19 | 20 |

21 |

22 | Playback Rate 1 23 |
24 |

25 | 26 | 27 | 28 | 29 | 30 | 31 | 47 | 48 | 49 | -------------------------------------------------------------------------------- /images/favicon-16x16.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperaudio/hyperaudio-lite-editor/f51106e7aed1fe47d1f43e0a897071c51221a5bb/images/favicon-16x16.png -------------------------------------------------------------------------------- /images/favicon-32x32.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperaudio/hyperaudio-lite-editor/f51106e7aed1fe47d1f43e0a897071c51221a5bb/images/favicon-32x32.png -------------------------------------------------------------------------------- /images/icon-192x192.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperaudio/hyperaudio-lite-editor/f51106e7aed1fe47d1f43e0a897071c51221a5bb/images/icon-192x192.png -------------------------------------------------------------------------------- /images/icon-512x512.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperaudio/hyperaudio-lite-editor/f51106e7aed1fe47d1f43e0a897071c51221a5bb/images/icon-512x512.png -------------------------------------------------------------------------------- /images/maskable-icon-192x192.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperaudio/hyperaudio-lite-editor/f51106e7aed1fe47d1f43e0a897071c51221a5bb/images/maskable-icon-192x192.png -------------------------------------------------------------------------------- /images/poster.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperaudio/hyperaudio-lite-editor/f51106e7aed1fe47d1f43e0a897071c51221a5bb/images/poster.png -------------------------------------------------------------------------------- /js/.prettierrc.json: -------------------------------------------------------------------------------- 1 | { 2 | "trailingComma": "all", 3 | "useTabs": false, 4 | "tabWidth": 2, 5 | "semi": true, 6 | "singleQuote": true, 7 | "arrowParens": "avoid", 8 | "printWidth": 120 9 | } -------------------------------------------------------------------------------- /js/audio-cut.js: -------------------------------------------------------------------------------- 1 | /** 2 | * Asynchronously cuts sections from an audio file. 3 | * 4 | * Version 0.1.2 5 | * 6 | * @param {ArrayBuffer} audioData - The ArrayBuffer of the audio file. 7 | * @param {number} startTime - The start time in seconds for the cut. 8 | * @param {number} endTime - The end time in seconds for the cut. 9 | * @returns {Promise} A Promise that resolves to the cut AudioBuffer. 10 | * 11 | * @example 12 | * // Assuming you have an ArrayBuffer of audio data 13 | * cutAudioFileAsync(audioData, 10, 20) 14 | * .then(cutBuffer => { 15 | * // Do something with the cut audio buffer 16 | * }) 17 | * .catch(error => {to_wav 18 | * console.error('Error cutting audio file:', error); 19 | * }); 20 | * 21 | * @description 22 | * This function takes an ArrayBuffer of an audio file and cuts a portion of it from startTime to endTime. 23 | * It returns a Promise that resolves to an AudioBuffer of the cut section. 24 | * The function utilizes the Web Audio API for decoding and manipulating the audio data. 25 | */ 26 | export async function cutAudioFileAsync(audioData, startTime, endTime) { 27 | const audioContext = new (window.AudioContext || window.webkitAudioContext)(); 28 | 29 | // Decode the audio asynchronously 30 | function decodeAudioDataAsync(audioContext, audioData) { 31 | return new Promise((resolve, reject) => { 32 | audioContext.decodeAudioData(audioData, resolve, reject); 33 | }); 34 | } 35 | 36 | try { 37 | const decodedData = await decodeAudioDataAsync(audioContext, audioData); 38 | const sampleRate = decodedData.sampleRate; 39 | const startOffset = startTime * sampleRate; 40 | const endOffset = endTime * sampleRate; 41 | 42 | // Create a new buffer for the desired part of the audio 43 | const cutBuffer = audioContext.createBuffer( 44 | decodedData.numberOfChannels, 45 | endOffset - startOffset, 46 | sampleRate 47 | ); 48 | 49 | // Copy the data into the new buffer 50 | for (let channel = 0; channel < decodedData.numberOfChannels; channel++) { 51 | const channelData = decodedData.getChannelData(channel); 52 | cutBuffer.copyToChannel( 53 | channelData.subarray(startOffset, endOffset), 54 | channel 55 | ); 56 | } 57 | 58 | return cutBuffer; 59 | } catch (e) { 60 | console.error("Error with decoding audio data", e); 61 | throw e; 62 | } 63 | } 64 | 65 | export async function convertAudioBufferToWavBlob(audioBuffer) { 66 | audioBuffer = convertMultiChannelToMono(audioBuffer); 67 | 68 | const numberOfChannels = audioBuffer.numberOfChannels; 69 | const sampleRate = audioBuffer.sampleRate; 70 | const format = 1; // PCM 71 | const bitDepth = 16; 72 | 73 | let bufferLength = 44; // Length of the WAV header 74 | for (let i = 0; i < numberOfChannels; i++) { 75 | bufferLength += audioBuffer.getChannelData(i).length * 2; // 2 bytes per sample 76 | } 77 | 78 | const buffer = new ArrayBuffer(bufferLength); 79 | const view = new DataView(buffer); 80 | 81 | // Scrivi l'header WAV 82 | writeString(view, 0, "RIFF"); // ChunkID 83 | view.setUint32(4, 36 + bufferLength - 44, true); // ChunkSize 84 | writeString(view, 8, "WAVE"); // Format 85 | writeString(view, 12, "fmt "); // Subchunk1ID 86 | view.setUint32(16, 16, true); // Subchunk1Size 87 | view.setUint16(20, format, true); // AudioFormat 88 | view.setUint16(22, numberOfChannels, true); // NumChannels 89 | view.setUint32(24, sampleRate, true); // SampleRate 90 | view.setUint32(28, sampleRate * numberOfChannels * 2, true); // ByteRate 91 | view.setUint16(32, numberOfChannels * 2, true); // BlockAlign 92 | view.setUint16(34, bitDepth, true); // BitsPerSample 93 | writeString(view, 36, "data"); // Subchunk2ID 94 | view.setUint32(40, bufferLength - 44, true); // Subchunk2Size 95 | 96 | // Write the audio samples 97 | let offset = 44; 98 | for (let channel = 0; channel < numberOfChannels; channel++) { 99 | const channelData = audioBuffer.getChannelData(channel); 100 | for (let i = 0; i < channelData.length; i++, offset += 2) { 101 | const sample = Math.max(-1, Math.min(1, channelData[i])); 102 | view.setInt16( 103 | offset, 104 | sample < 0 ? sample * 0x8000 : sample * 0x7fff, 105 | true 106 | ); 107 | } 108 | } 109 | 110 | return new Blob([view], { type: "audio/wav" }); 111 | } 112 | 113 | function writeString(view, offset, string) { 114 | for (let i = 0; i < string.length; i++) { 115 | view.setUint8(offset + i, string.charCodeAt(i)); 116 | } 117 | } 118 | 119 | function convertMultiChannelToMono(audioBuffer) { 120 | const numberOfChannels = audioBuffer.numberOfChannels; 121 | 122 | // Crea un nuovo AudioBuffer mono 123 | const monoBuffer = new AudioBuffer({ 124 | length: audioBuffer.length, 125 | sampleRate: audioBuffer.sampleRate, 126 | numberOfChannels: 1, 127 | }); 128 | 129 | const monoChannel = monoBuffer.getChannelData(0); 130 | 131 | // Mixdown dei canali 132 | for (let i = 0; i < audioBuffer.length; i++) { 133 | let sum = 0; 134 | for (let channel = 0; channel < numberOfChannels; channel++) { 135 | sum += audioBuffer.getChannelData(channel)[i]; 136 | } 137 | monoChannel[i] = sum / numberOfChannels; 138 | } 139 | 140 | return monoBuffer; 141 | } 142 | 143 | /** 144 | * Represents audio data including its URL, start and stop times, and an AudioBuffer. 145 | * 146 | * @example 147 | * // Example usage: 148 | * let myAudioData = new AudioData('http://example.com/audio.wav', 0, 10); 149 | * // Later on, you can set the AudioBuffer 150 | * myAudioData.setAudioBuffer(loadedAudioBuffer); 151 | */ 152 | export class AudioData { 153 | /** 154 | * Constructs an instance of AudioData. 155 | * @param {string} url - The URL of the audio file. 156 | * @param {number} start - The start time of the audio segment in seconds. 157 | * @param {number} stop - The stop time of the audio segment in seconds. 158 | */ 159 | static audioBuffers = []; 160 | 161 | constructor(url, start, stop) { 162 | this.url = url; // URL of the audio file 163 | this.start = start; // Start time of the audio segment (in seconds) 164 | this.stop = stop; // Stop time of the audio segment (in seconds) 165 | this.audioBuffer = null; // AudioBuffer, initially set to null 166 | } 167 | 168 | static clearAudioBuffers() { 169 | AudioData.audioBuffers = []; 170 | } 171 | 172 | /** 173 | * Sets the AudioBuffer for this audio data. 174 | * @param {AudioBuffer} audioBuffer - The AudioBuffer to be associated with this audio data. 175 | */ 176 | setAudioBuffer(audioBuffer) { 177 | this.audioBuffer = audioBuffer; 178 | AudioData.audioBuffers.push(audioBuffer); 179 | } 180 | 181 | static getAllAudioBuffers() { 182 | return AudioData.audioBuffers; 183 | } 184 | 185 | // Add any other methods that might be useful for this class 186 | } 187 | export function concatenateAudioBuffers(audioBuffers) { 188 | // Assicurati che ci siano AudioBuffer da concatenare 189 | try { 190 | if (audioBuffers.length === 0) { 191 | throw new Error("No audio buffers to concatenate"); 192 | } 193 | } catch (error) { 194 | console.log(error); 195 | } 196 | 197 | 198 | // Calculate the total length of the buffer 199 | const totalLength = audioBuffers.reduce( 200 | (sum, buffer) => sum + buffer.length, 201 | 0 202 | ); 203 | 204 | // Create a ew AuidoBuffer to contain the concatenated data 205 | const sampleRate = audioBuffers[0].sampleRate; // Assume all buffers have the same sample frequency 206 | const concatenatedBuffer = new AudioContext().createBuffer( 207 | audioBuffers[0].numberOfChannels, 208 | totalLength, 209 | sampleRate 210 | ); 211 | 212 | // Copy the data into one buffer 213 | let offset = 0; 214 | audioBuffers.forEach((buffer) => { 215 | for (let channel = 0; channel < buffer.numberOfChannels; channel++) { 216 | concatenatedBuffer 217 | .getChannelData(channel) 218 | .set(buffer.getChannelData(channel), offset); 219 | } 220 | offset += buffer.length; 221 | }); 222 | 223 | return concatenatedBuffer; 224 | } 225 | 226 | // export function fetchAudioBuffer(audioDataArray) { 227 | // // Usa map per creare un array di promesse 228 | // const promises = audioDataArray.map(async (audiodata) => { 229 | // const response = await fetch(audiodata.url); 230 | // console.log("file download"); 231 | // const arrayBuffer = await response.arrayBuffer(); 232 | // console.log("file buffer"); 233 | // console.log(arrayBuffer); 234 | // const cutBuffer = await cutAudioFileAsync( 235 | // arrayBuffer, 236 | // audiodata.start, 237 | // audiodata.stop 238 | // ); 239 | // console.log("file cut"); 240 | // console.log(cutBuffer); 241 | // audiodata.setAudioBuffer(cutBuffer); 242 | // }); 243 | 244 | // // Restituisce una promessa che si risolve quando tutte le promesse nell'array sono risolte 245 | // return Promise.all(promises); 246 | // } 247 | 248 | export async function fetchAudioBuffer(audioDataArray) { 249 | // Arrays to keep track of processed audio buffers 250 | let processedAudioBuffers = []; 251 | 252 | for (const audiodata of audioDataArray) { 253 | try { 254 | // Download data as ArrayBuffer 255 | const response = await fetch(audiodata.url); 256 | const arrayBuffer = await response.arrayBuffer(); 257 | 258 | // Trims the audio buffer based on the specified start and end times 259 | const cutBuffer = await cutAudioFileAsync( 260 | arrayBuffer, 261 | audiodata.start, 262 | audiodata.stop 263 | ); 264 | 265 | // Sets the trimmed audio buffer for the current AudioData object 266 | audiodata.setAudioBuffer(cutBuffer); 267 | 268 | // Add the trimmed audio buffer to the processed buffer array 269 | processedAudioBuffers.push(cutBuffer); 270 | } catch (error) { 271 | alert("File must exist, be referenced locally or CORS enabled on the server."); 272 | break; 273 | } 274 | } 275 | 276 | // Returns the array of processed audio buffers, maintaining order 277 | return processedAudioBuffers; 278 | } 279 | 280 | async function testData(url) { 281 | try { 282 | const response = await fetch(url); 283 | if (!response.ok) { 284 | throw new Error(`HTTP error, status = ${response.status}`); 285 | } 286 | return await response.json(); 287 | } catch (error) { 288 | console.error("Error fetching data:", error); 289 | if (error.name === "TypeError" && error.message.includes("fetch")) { 290 | console.error("This error may be related to CORS."); 291 | } 292 | // Handle error appropriately 293 | return null; 294 | } 295 | } 296 | 297 | export function printAudioBuffersDetails() { 298 | const allAudioBuffers = AudioData.getAllAudioBuffers(); 299 | allAudioBuffers.forEach((audioBuffer, index) => { 300 | // console.dir(audioBuffer); 301 | // console.log(`AudioBuffer ${index}:`); 302 | // Here you can access specific properties of the AudioBuffer 303 | // For example, length, duration, sampleRate, etc. 304 | // console.log(` Length: ${audioBuffer.length}`); 305 | // console.log(` Duration: ${audioBuffer.duration}`); 306 | // console.log(` Sample Rate: ${audioBuffer.sampleRate}`); 307 | // Aggiungi altre proprietà che desideri visualizzare 308 | }); 309 | } 310 | 311 | export async function cutAudio(audioDataArray) { 312 | await fetchAudioBuffer(audioDataArray); 313 | console.log(audioDataArray); 314 | console.log(`allAudioBuffer ${AudioData.getAllAudioBuffers()} --- `); 315 | printAudioBuffersDetails(); 316 | 317 | const cutBuffer = concatenateAudioBuffers(AudioData.getAllAudioBuffers()); 318 | const wavBlob = await convertAudioBufferToWavBlob(cutBuffer); 319 | AudioData.clearAudioBuffers(); 320 | return wavBlob; 321 | } 322 | 323 | export function to_wav(wavBlob, download_name) { 324 | const url = URL.createObjectURL(wavBlob); 325 | 326 | // Create to allow download 327 | const a = document.createElement("a"); 328 | a.href = url; 329 | a.download = `${download_name}.wav`; // Note the file will be WAV not mp3 330 | document.body.appendChild(a); 331 | a.click(); 332 | 333 | // Clean up 334 | document.body.removeChild(a); 335 | URL.revokeObjectURL(url); 336 | } 337 | 338 | export function playAudio(wavBlob, audioElementId) { 339 | const url = URL.createObjectURL(wavBlob); 340 | const audioElement = document.getElementById(audioElementId); 341 | audioElement.src = url; 342 | } 343 | 344 | export const cutAudioApp = { 345 | cutAudio: cutAudio, 346 | to_wav: to_wav, 347 | playAudio: playAudio, 348 | }; 349 | -------------------------------------------------------------------------------- /js/caption-modified.js: -------------------------------------------------------------------------------- 1 | /*! (C) The Hyperaudio Project. MIT @license: en.wikipedia.org/wiki/MIT_License. */ 2 | /*! Version 2.1.3 */ 3 | 'use strict'; 4 | 5 | var caption = function () { 6 | var cap = {}; 7 | 8 | function formatSeconds(seconds) { 9 | if (typeof seconds == 'number') { 10 | //console.log("seconds = "+seconds); 11 | return new Date(seconds.toFixed(3) * 1000).toISOString().substring(11,23); 12 | } else { 13 | console.log('warning - attempting to format the non number: ' + seconds); 14 | return null; 15 | } 16 | } 17 | 18 | function convertTimecodeToSrt(timecode) { 19 | //the same as VTT format but milliseconds separated by a comma 20 | return timecode.substring(0,8) + "," + timecode.substring(9,12); 21 | } 22 | 23 | cap.init = function (transcriptId, playerId, maxLength, minLength, label, srclang, parent) { 24 | 25 | var transcript = document.getElementById(transcriptId); 26 | 27 | if (parent) { 28 | const parser = new DOMParser(); 29 | const doc = parser.parseFromString(parent.innerHTML, 'text/html'); 30 | transcript = doc.getElementById(transcriptId); 31 | } 32 | 33 | var words = transcript.querySelectorAll('[data-m]'); 34 | var data = {}; 35 | data.segments = []; 36 | 37 | function segmentMeta(speaker, start, duration, chars) { 38 | this.speaker = speaker; 39 | this.start = start; 40 | this.duration = duration; 41 | this.chars = chars; 42 | this.words = []; 43 | } 44 | 45 | function wordMeta(start, duration, text) { 46 | this.start = start; 47 | this.duration = duration; 48 | this.text = text; 49 | } 50 | 51 | var thisWordMeta; 52 | var thisSegmentMeta = null; 53 | 54 | // defaults 55 | var maxLineLength = 37; 56 | var minLineLength = 21; 57 | var maxWordDuration = 2; //seconds 58 | 59 | var captionsVtt = 'WEBVTT\n'; 60 | var captionsSrt = ''; 61 | 62 | var endSentenceDelimiter = /[\.。?؟!]/g; 63 | var midSentenceDelimiter = /[,、–,،و:,…‥]/g; 64 | 65 | if (!isNaN(maxLength) && maxLength != null) { 66 | maxLineLength = maxLength; 67 | } 68 | 69 | if (!isNaN(minLength) && minLength != null) { 70 | minLineLength = minLength; 71 | } 72 | 73 | var lastSpeaker = ''; 74 | 75 | words.forEach(function (word, i) { 76 | if (thisSegmentMeta === null) { 77 | // create segment meta object 78 | thisSegmentMeta = new segmentMeta('', null, 0, 0, 0); 79 | } 80 | 81 | if (word.classList.contains('speaker')) { 82 | // checking that this is not a new segment AND a new empty segment wasn't already created 83 | if (thisSegmentMeta !== null && thisSegmentMeta.start !== null) { 84 | data.segments.push(thisSegmentMeta); // push the previous segment because it's a new speaker 85 | thisSegmentMeta = new segmentMeta('', null, 0, 0, 0); 86 | } 87 | 88 | thisSegmentMeta.speaker = word.innerText; 89 | } else { 90 | var thisStart = parseInt(word.getAttribute('data-m')) / 1000; 91 | var thisDuration = parseInt(word.getAttribute('data-d')) / 1000; 92 | 93 | if (isNaN(thisStart)) { 94 | thisStart = 0; 95 | } 96 | 97 | // data-d (duration) is an optional attribute, if it doesn't exist 98 | // use the start time of the next word (if it exists) or for the last word 99 | // pick a sensible duration. 100 | 101 | if (isNaN(thisDuration)) { 102 | if (i < (words.length - 1)) { 103 | thisDuration = (parseInt(words[i+1].getAttribute('data-m') - 1) / 1000) - thisStart; 104 | if (thisDuration > maxWordDuration) { 105 | thisDuration = maxWordDuration; 106 | } 107 | } else { 108 | thisDuration = 5; // sensible default for the last word 109 | } 110 | } 111 | 112 | var thisText = word.innerText; 113 | 114 | thisWordMeta = new wordMeta(thisStart, thisDuration, thisText); 115 | 116 | if (thisSegmentMeta.start === null) { 117 | thisSegmentMeta.start = thisStart; 118 | thisSegmentMeta.duration = 0; 119 | thisSegmentMeta.chars = 0; 120 | } 121 | 122 | thisSegmentMeta.duration += thisDuration; 123 | thisSegmentMeta.chars += thisText.length; 124 | 125 | thisSegmentMeta.words.push(thisWordMeta); 126 | 127 | // remove spaces first just in case 128 | var lastChar = thisText.replace(/\s/g, '').slice(-1); 129 | if (lastChar.match(endSentenceDelimiter)) { 130 | data.segments.push(thisSegmentMeta); 131 | thisSegmentMeta = null; 132 | } 133 | } 134 | }); 135 | 136 | //console.log(data.segments); 137 | 138 | function captionMeta(start, stop, text) { 139 | this.start = start; 140 | this.stop = stop; 141 | this.text = text; 142 | } 143 | 144 | var captions = []; 145 | var thisCaption = null; 146 | 147 | data.segments.map(function (segment, i, arr) { 148 | // If the entire segment fits on a line, add it to the captions. 149 | if (segment.chars < maxLineLength) { 150 | 151 | if (segment.duration === 0){ 152 | if (i < arr.length) { 153 | segment.duration = arr[i+1].start - segment.start; 154 | } else { 155 | segment.duration = 5 * 1000; 156 | } 157 | } 158 | 159 | thisCaption = new captionMeta( 160 | formatSeconds(segment.start), 161 | formatSeconds(segment.start + segment.duration), 162 | '', 163 | ); 164 | 165 | segment.words.forEach(function (wordMeta) { 166 | thisCaption.text += wordMeta.text; 167 | }); 168 | 169 | thisCaption.text += '\n'; 170 | //console.log("0. pushing because the whole segment fits on a line!"); 171 | //console.log(thisCaption); 172 | captions.push(thisCaption); 173 | thisCaption = null; 174 | } else { 175 | // The number of chars in this segment is longer than our single line maximum 176 | 177 | var charCount = 0; 178 | var lineText = ''; 179 | var firstLine = true; 180 | var lastOutTime; 181 | var lastInTime = null; 182 | 183 | segment.words.forEach(function (wordMeta, index) { 184 | var lastChar = wordMeta.text.replace(/\s/g, '').slice(-1); 185 | 186 | if (lastInTime === null) { 187 | // if it doesn't exist yet set the caption start time to the word's start time. 188 | lastInTime = wordMeta.start; 189 | } 190 | 191 | // Are we over the minimum length of a line and hitting a good place to split mid-sentence? 192 | if (charCount + wordMeta.text.length > minLineLength && lastChar.match(midSentenceDelimiter)) { 193 | if (firstLine === true) { 194 | thisCaption = new captionMeta( 195 | formatSeconds(lastInTime), 196 | formatSeconds(wordMeta.start + wordMeta.duration), 197 | '', 198 | ); 199 | thisCaption.text += lineText + wordMeta.text + '\n'; 200 | 201 | //check for last word in segment, if it is we can push a one line caption, if not – move on to second line 202 | 203 | if (index + 1 >= segment.words.length) { 204 | //console.log("1. pushing because we're at a good place to split, we're on the first line but it's the last word of the segment."); 205 | //console.log(thisCaption); 206 | captions.push(thisCaption); 207 | thisCaption = null; 208 | } else { 209 | firstLine = false; 210 | } 211 | } else { 212 | // We're on the second line ... we're over the minimum chars and in a good place to split – let's push the caption 213 | 214 | thisCaption.stop = formatSeconds(wordMeta.start + wordMeta.duration); 215 | thisCaption.text += lineText + wordMeta.text; 216 | //console.log("2. pushing because we're on the second line and have a good place to split"); 217 | //console.log(thisCaption); 218 | captions.push(thisCaption); 219 | thisCaption = null; 220 | firstLine = true; 221 | } 222 | 223 | // whether first line or not we should reset ready for a new caption 224 | charCount = 0; 225 | lineText = ''; 226 | lastInTime = null; 227 | } else { 228 | // we're not over the minimum length with a suitable splitting point 229 | 230 | // If we add this word are we over the maximum? 231 | if (charCount + wordMeta.text.length > maxLineLength) { 232 | if (firstLine === true) { 233 | if (lastOutTime === undefined) { 234 | lastOutTime = wordMeta.start + wordMeta.duration; 235 | } 236 | 237 | thisCaption = new captionMeta(formatSeconds(lastInTime), formatSeconds(lastOutTime), ''); 238 | thisCaption.text += lineText + '\n'; 239 | 240 | // It's just the first line so we should only push a new caption if it's the very last word! 241 | 242 | if (index >= segment.words.length) { 243 | captions.push(thisCaption); 244 | thisCaption = null; 245 | } else { 246 | firstLine = false; 247 | } 248 | } else { 249 | // We're on the second line and since we're over the maximum with the next word we should push this caption! 250 | 251 | thisCaption.stop = formatSeconds(lastOutTime); 252 | thisCaption.text += lineText; 253 | 254 | captions.push(thisCaption); 255 | 256 | thisCaption = null; 257 | firstLine = true; 258 | } 259 | 260 | // do the stuff we need to do to start a new line 261 | charCount = wordMeta.text.length; 262 | lineText = wordMeta.text; 263 | lastInTime = wordMeta.start; // Why do we do this?????? 264 | } else { 265 | // We're not over the maximum with this word, update the line length and add the word to the text 266 | 267 | charCount += wordMeta.text.length; 268 | lineText += wordMeta.text; 269 | } 270 | } 271 | 272 | // for every word update the lastOutTime 273 | lastOutTime = wordMeta.start + wordMeta.duration; 274 | }); 275 | 276 | // we're out of words for this segment - decision time! 277 | if (thisCaption !== null) { 278 | // The caption had been started, time to add whatever text we have and add a stop point 279 | thisCaption.stop = formatSeconds(lastOutTime); 280 | thisCaption.text += lineText; 281 | //console.log("3. pushing at end of segment when new caption HAS BEEN created"); 282 | //console.log(thisCaption); 283 | captions.push(thisCaption); 284 | thisCaption = null; 285 | } else { 286 | // caption hadn't been started yet - create one! 287 | if (lastInTime !== null) { 288 | thisCaption = new captionMeta(formatSeconds(lastInTime), formatSeconds(lastOutTime), lineText); 289 | //console.log("4. pushing at end of segment when new caption has yet to be created"); 290 | //console.log(thisCaption); 291 | captions.push(thisCaption); 292 | thisCaption = null; 293 | } 294 | } 295 | } 296 | }); 297 | 298 | //console.log("start creating captions"); 299 | 300 | captions.forEach(function (caption, i) { 301 | captionsVtt += '\n' + caption.start + ' --> ' + caption.stop + '\n' + caption.text + '\n'; 302 | //console.log(caption.start + ' --> ' + caption.stop + '\n' + caption.text); 303 | captionsSrt += '\n' + (i + 1) + '\n' + convertTimecodeToSrt(caption.start) + ' --> ' + convertTimecodeToSrt(caption.stop) + '\n' + caption.text + '\n'; 304 | }); 305 | 306 | var video = document.getElementById(playerId); 307 | 308 | if (video !== null) { 309 | video.addEventListener("loadedmetadata", function listener() { 310 | //var track = document.createElement("track"); 311 | var track = document.getElementById(playerId+'-vtt'); 312 | track.kind = "captions"; 313 | 314 | //console.log("label = "+label); 315 | 316 | if (label !== undefined) { 317 | //console.log("setting label as "+label); 318 | track.label = label; 319 | } 320 | 321 | if (srclang !== undefined) { 322 | //console.log("setting srclang as "+srclang); 323 | track.srclang = srclang; 324 | } 325 | //track.label = "English"; 326 | //track.srclang = "en"; 327 | track.src = "data:text/vtt,"+encodeURIComponent(captionsVtt); 328 | video.textTracks[0].mode = "showing"; 329 | video.removeEventListener("loadedmetadata", listener, true); 330 | }, true); 331 | 332 | video.textTracks[0].mode = "showing"; 333 | } 334 | 335 | function captionsObj(vtt, srt, data) { 336 | // clean up – remove any double blank lines 337 | // and blank line at the start of srt 338 | 339 | if (srt.charAt(0) !== "1") { 340 | srt = srt.slice(1); 341 | } 342 | 343 | this.vtt = vtt.replaceAll("\n\n\n","\n\n"); 344 | this.srt = srt.replaceAll("\n\n\n","\n\n"); 345 | this.data = captions; 346 | } 347 | 348 | return new captionsObj(captionsVtt, captionsSrt, captions); 349 | }; 350 | 351 | return cap; 352 | }; 353 | -------------------------------------------------------------------------------- /js/hyperaudio-lite-editor-deepgram.js: -------------------------------------------------------------------------------- 1 | /*! (C) The Hyperaudio Project. MIT @license: en.wikipedia.org/wiki/MIT_License. */ 2 | /*! Version 1.0.2 */ 3 | 4 | class DeepgramService extends HTMLElement { 5 | 6 | constructor() { 7 | super(); 8 | } 9 | 10 | configureLanguage() { 11 | 12 | populateLanguageDeepgram(); 13 | 14 | const selectModel = document.querySelector('#deepgram-form #language-model'); 15 | const optionLanguageModel = { 16 | "General": "general", 17 | "Whisper (Tiny)": "whisper-tiny", 18 | "Whisper (Base)": "whisper-base", 19 | "Whisper (Small)": "whisper-small", 20 | "Whisper (Medium)": "whisper-medium", 21 | "Whisper (Large)": "whisper-large", 22 | "Meeting": "meeting", 23 | "Phone call": "phonecall", 24 | "Voicemail": "voicemail", 25 | "Finance": "finance", 26 | "Conversational AI": "conversationalai", 27 | "Video": "video", 28 | "Medical": "medical" 29 | } 30 | 31 | let counter = 0 32 | Object.keys(optionLanguageModel).forEach( model => { 33 | let option = document.createElement("option") 34 | option.value = optionLanguageModel[model] 35 | option.innerHTML = `${model}` 36 | if (counter === 0) { 37 | option.selected = "selected" 38 | } 39 | selectModel.appendChild(option); 40 | counter += 1; 41 | } ); 42 | } 43 | 44 | clearMediaUrl(event) { 45 | event.preventDefault(); 46 | document.querySelector('#deepgram-media').value = ""; 47 | } 48 | 49 | clearFilePicker(event) { 50 | event.preventDefault(); 51 | document.querySelector('#deepgram-file').value = ""; 52 | } 53 | 54 | updatePlayerWithLocalFile(event) { 55 | const file = document.querySelector('#deepgram-file').files[0]; 56 | // Create a new FileReader instance 57 | const reader = new FileReader(); 58 | 59 | reader.readAsArrayBuffer(file); 60 | let blob = null; 61 | 62 | reader.addEventListener('load', () => { 63 | 64 | file.arrayBuffer().then((arrayBuffer) => { 65 | blob = new Blob([new Uint8Array(arrayBuffer)], {type: file.type }); 66 | 67 | let player = document.querySelector("#hyperplayer"); 68 | player.src = URL.createObjectURL(blob); 69 | }); 70 | }); 71 | } 72 | 73 | updateDropdowns(event) { 74 | let model = document.querySelector('#deepgram-form #language-model').value; 75 | 76 | // update languages depending on model 77 | if (model.startsWith("whisper")){ 78 | populateLanguageWhisper(); 79 | } else { 80 | if (model === "general") { 81 | populateLanguageDeepgram(); 82 | } else { 83 | populateLanguageDeepgramRestricted(); 84 | } 85 | } 86 | } 87 | 88 | updateLanguageDropdown(event) { 89 | let tier = document.querySelector('#deepgram-form #tier').value; 90 | 91 | console.log(tier); 92 | 93 | if (tier === "base" || tier === "enhanced" ){ 94 | populateLanguageDeepgram(); 95 | } 96 | 97 | if (tier === "nova"){ 98 | populateLanguageDeepgramRestricted(); 99 | } 100 | } 101 | 102 | updateTierDropdown(event) { 103 | 104 | const deepgramModelCompatibility = { 105 | "zh_general": ["base"], 106 | "zh-CN_general": ["base"], 107 | "zh-TW_general": ["base"], 108 | "da_general": ["enhanced", "base"], 109 | "nl_general": ["enhanced", "base"], 110 | "en_general": ["nova", "enhanced", "base"], 111 | "en_meeting": ["nova", "enhanced", "base"], 112 | "en_phonecall": ["nova", "enhanced", "base"], 113 | "en_voicemail": ["nova", "base"], 114 | "en_finance": ["nova", "enhanced", "base"], 115 | "en_conversationalai": ["nova", "base"], 116 | "en_video": ["nova","base"], 117 | "en_medical": ["nova"], 118 | "en-AU_general": ["nova", "base"], 119 | "en-GB_general": ["nova", "base"], 120 | "en-IN_general": ["nova", "base"], 121 | "en-NZ_general": ["nova", "base"], 122 | "en-US_general": ["nova", "enhanced", "base"], 123 | "en-US_meeting": ["nova","enhanced", "base"], 124 | "en-US_phonecall": ["nova", "enhanced", "base"], 125 | "en-US_voicemail": ["nova","base"], 126 | "en-US_finance": ["nova","enhanced", "base"], 127 | "en-US_conversationalai": ["nova","base"], 128 | "en-US_video": ["nova", "base"], 129 | "en-US_medical": ["nova"], 130 | "nl_general": ["enhanced", "base"], 131 | "fr_general": ["enhanced" , "base"], 132 | "fr-CA_general": ["base"], 133 | "de_general": ["enhanced", "base"], 134 | "hi_general": ["enhanced", "base"], 135 | "hi-Latn_general": ["base"], 136 | "id_general": ["base"], 137 | "it_general": ["enhanced", "base"], 138 | "ja_general": ["enhanced", "base"], 139 | "ko_general": ["enhanced", "base"], 140 | "no_general":["enhanced", "base"], 141 | "pl_general":["enhanced", "base"], 142 | "pt_general": ["enhanced", "base"], 143 | "pt-BR_general": ["enhanced", "base"], 144 | "pt-PT_general": ["enhanced", "base"], 145 | "ru_general": ["base"], 146 | "es_general": ["enhanced", "base"], 147 | "es-419_general": ["enhanced", "base"], 148 | "sv_general": ["enhanced", "base"], 149 | "ta_general": ["enhanced"], 150 | "tr_general": ["base"], 151 | "uk_general": ["base"] 152 | } 153 | 154 | let model = document.querySelector('#deepgram-form #language-model').value; 155 | let lang = document.querySelector('#deepgram-form #language').value; 156 | let tiers = deepgramModelCompatibility[lang+"_"+model]; 157 | 158 | let options = document.querySelector('#tier').options; 159 | 160 | for (let option of options) { 161 | option.disabled = true; 162 | if (typeof tiers !== "undefined" && tiers.length > 0 && tiers.includes(option.value)) { 163 | option.disabled = false; 164 | } 165 | }; 166 | } 167 | 168 | getData(event) { 169 | document.querySelector('#hypertranscript').innerHTML = '
Transcribing....

transcribing
'; 170 | const language = document.querySelector('#language').value; 171 | const model = document.querySelector('#language-model').value; 172 | let media = document.querySelector('#deepgram-media').value; 173 | const token = document.querySelector('#token').value; 174 | const file = document.querySelector('#deepgram-file').files[0]; 175 | let tier = document.querySelector('#tier').value; 176 | 177 | if (media.toLowerCase().startsWith("https://") === false && media.toLowerCase().startsWith("http://") === false) { 178 | media = "https://"+media; 179 | } 180 | 181 | if (file !== undefined) { 182 | fetchDataLocal(token, file, tier, language, model); 183 | document.querySelector('#deepgram-media').value = ""; 184 | } else { 185 | if (media !== "" || token !== "") { 186 | let player = document.querySelector("#hyperplayer"); 187 | player.src = media; 188 | fetchData(token, media, tier, language, model); 189 | } else { 190 | document.querySelector('#hypertranscript').innerHTML = '
error
Please include both a link to the media and token in the form.
'; 191 | } 192 | } 193 | } 194 | 195 | connectedCallback() { 196 | 197 | let template = null; 198 | let modal = this; 199 | 200 | const templateUrl = this.getAttribute("templateUrl"); 201 | const templateSelector = this.getAttribute("templateSelector"); 202 | 203 | if (templateUrl !== null) { 204 | fetch(templateUrl) 205 | .then(function(response) { 206 | // When the page is loaded convert it to text 207 | return response.text() 208 | }) 209 | .then(function(html) { 210 | // Initialize the DOM parser 211 | let parser = new DOMParser(); 212 | 213 | // Parse the text 214 | template = parser.parseFromString(html, "text/html"); 215 | let deepgramTempl = template.querySelector('#deepgram-modal-template').cloneNode(true); 216 | modal.innerHTML = deepgramTempl.innerHTML; 217 | modal.configureLanguage(); 218 | addModalEventListeners(modal); 219 | }) 220 | .catch(function(err) { 221 | console.log('Template error: ', err); 222 | }); 223 | } else { 224 | modal.innerHTML = document.querySelector(templateSelector).innerHTML; 225 | document.querySelector(templateSelector).remove(); 226 | modal.configureLanguage(); 227 | addModalEventListeners(modal); 228 | } 229 | } 230 | } 231 | 232 | customElements.define('deepgram-service', DeepgramService); 233 | 234 | function addModalEventListeners(modal) { 235 | document.querySelector('#deepgram-file').addEventListener('change',modal.clearMediaUrl); 236 | document.querySelector('#deepgram-media').addEventListener('change',modal.clearFilePicker); 237 | document.querySelector('#transcribe-btn').addEventListener('click', modal.getData); 238 | document.querySelector('#deepgram-file').addEventListener('change', modal.updatePlayerWithLocalFile); 239 | document.querySelector('#language-model').addEventListener('change', modal.updateDropdowns); 240 | document.querySelector('#language-model').addEventListener('change', modal.updateTierDropdown); 241 | document.querySelector('#language').addEventListener('change', modal.updateTierDropdown); 242 | document.querySelector('#tier').addEventListener('change', modal.updateLanguageDropdown); 243 | } 244 | 245 | function fetchData(token, media, tier, language, model) { 246 | 247 | let url = getApiUrl(tier, language, model); 248 | 249 | fetch(url, { 250 | method: 'POST', 251 | headers: { 252 | 'Authorization': 'Token '+token+'', 253 | 'content-type': 'application/json' 254 | }, 255 | body: JSON.stringify({ 256 | 'url': media 257 | }) 258 | }) 259 | .then(response => { 260 | if (!response.ok) { 261 | throw new Error(response.status); 262 | } else { 263 | console.log("response ok"); 264 | } 265 | 266 | return response.json(); 267 | }) 268 | .then(json => { 269 | console.dir(json); 270 | 271 | if (json.results.channels[0] === undefined || json.results.channels[0].alternatives[0].words.length === 0) { 272 | displayNoWordsError(); 273 | } else { 274 | parseData(json); 275 | } 276 | }) 277 | .catch(function (error) { 278 | displayAppropriateErrorMessage(error, token, media, tier, language, model, false); 279 | }) 280 | } 281 | 282 | function fetchDataLocal(token, file, tier, language, model) { 283 | 284 | const apiKey = token; 285 | 286 | // Create a new FileReader instance 287 | const reader = new FileReader(); 288 | 289 | reader.readAsArrayBuffer(file); 290 | let blob = null; 291 | 292 | reader.addEventListener('load', () => { 293 | 294 | file.arrayBuffer().then((arrayBuffer) => { 295 | blob = new Blob([new Uint8Array(arrayBuffer)], {type: file.type }); 296 | 297 | let player = document.querySelector("#hyperplayer"); 298 | player.src = URL.createObjectURL(blob); 299 | 300 | let url = getApiUrl(tier, language, model); 301 | 302 | // if the token is not present we just add the media to the player 303 | if (token !== "") { 304 | fetch(url, { 305 | method: 'POST', 306 | headers: { 307 | 'Authorization': 'Token ' + apiKey, 308 | 'Content-Type': file.type 309 | }, 310 | body: blob 311 | }) 312 | .then(response => { 313 | if (!response.ok) { 314 | throw new Error(response.status); 315 | } else { 316 | console.log("response ok"); 317 | } 318 | return response.json(); 319 | }) 320 | .then(json => { 321 | // check to see if any transcript data has come back before proceeding, give error message if not 322 | if (json.results.channels[0] === undefined || json.results.channels[0].alternatives[0].words.length === 0) { 323 | displayNoWordsError(); 324 | } else { 325 | parseData(json); 326 | } 327 | }) 328 | .catch(function (error) { 329 | displayAppropriateErrorMessage(error, token, file, tier, language, model, true); 330 | }) 331 | } else { 332 | document.querySelector('#hypertranscript').innerHTML = ''; 333 | } 334 | }); 335 | }); 336 | } 337 | 338 | function getApiUrl(tier, language, model) { 339 | let url = null; 340 | let languageParam = `&language=${language}`; 341 | if (language === "xx") { 342 | //signifies autodetect 343 | languageParam = "&detect_language=true"; 344 | } 345 | 346 | let novaPrefix = ""; 347 | if (tier === "nova") { 348 | novaPrefix = "2-"; 349 | } 350 | 351 | if (model.startsWith("whisper")) { // no tier 352 | url = `https://api.deepgram.com/v1/listen?model=${model}${languageParam}&diarize=true&summarize=true&detect_topics=true&smart_format=true` 353 | } else { 354 | url = `https://api.deepgram.com/v1/listen?model=${novaPrefix}${model}&tier=${tier}&diarize=true&summarize=true&detect_topics=true&language=${language}&smart_format=true` 355 | } 356 | return (url); 357 | } 358 | 359 | function displayAppropriateErrorMessage(error, token, file, tier, language, model, isLocal) { 360 | console.dir("error is : "+error); 361 | 362 | error = error + ""; 363 | 364 | let errorDisplayed = displayError(error, tier); 365 | 366 | if (error.indexOf("400") > 0 && tier === "enhanced") { 367 | tier = "base"; 368 | if (isLocal === true) { 369 | fetchDataLocal(token, file, tier, language, model); 370 | } else { 371 | fetchData(token, file, tier, language, model); 372 | } 373 | 374 | displayRetryError(); 375 | errorDisplayed = true; 376 | } 377 | 378 | if (error.indexOf("400") > 0 && tier === "nova") { 379 | tier = "enhanced"; 380 | if (isLocal === true) { 381 | fetchDataLocal(token, file, tier, language, model); 382 | } else { 383 | fetchData(token, file, tier, language, model); 384 | } 385 | 386 | displayRetryError(); 387 | errorDisplayed = true; 388 | } 389 | 390 | this.dataError = true; 391 | 392 | if (errorDisplayed === false) { 393 | displayGenericError(); 394 | } 395 | } 396 | 397 | function displayError(error, tier) { 398 | if (error.indexOf("401") > 0 || (error.indexOf("400") > 0 && tier === "base")) { 399 | document.querySelector('#hypertranscript').innerHTML = '
error
Sorry.
It appears that the media URL does not exist
or the token is invalid.
'; 400 | return true; 401 | } 402 | if (error.indexOf("402") > 0) { 403 | document.querySelector('#hypertranscript').innerHTML = '
error
Sorry.
It appears that the token is invalid.
'; 404 | return true; 405 | } 406 | return false; 407 | } 408 | 409 | function displayGenericError() { 410 | document.querySelector('#hypertranscript').innerHTML = '
error
Sorry.
An unexpected error has occurred.
'; 411 | } 412 | 413 | function displayRetryError() { 414 | document.querySelector('#hypertranscript').innerHTML = '
error
There appears to be a language / model incompatibility. Retrying with a different model.
'; 415 | } 416 | 417 | function displayNoWordsError() { 418 | document.querySelector('#hypertranscript').innerHTML = '
error
Sorry.
No words were detected.
Please verify that audio contains speech.
'; 419 | } 420 | 421 | 422 | function getLanguageCode(json){ 423 | // prepare the VTT track so that the correct language is defined 424 | 425 | let language = document.querySelector('#language').value; 426 | 427 | if (language === undefined) { 428 | let detectedLanguage = extractLanguage(json); 429 | if (detectedLanguage !== undefined) { 430 | language = detectedLanguage; 431 | } else { 432 | language = "language unknown"; 433 | } 434 | } 435 | 436 | return (language); 437 | } 438 | 439 | function parseData(json) { 440 | 441 | const maxWordsInPara = 100; 442 | const significantGapInSeconds = 0.5; 443 | 444 | const punctuatedWords = json.results.channels[0].alternatives[0].transcript.split(' '); 445 | const wordData = json.results.channels[0].alternatives[0].words; 446 | console.log("wordData..."); 447 | console.log(wordData); 448 | 449 | let hyperTranscript = "
\n
\n

\n "; 450 | 451 | let previousElementEnd = 0; 452 | let wordsInPara = 0; 453 | let showDiarization = true; 454 | 455 | if (document.querySelector("#summary") !== null) { 456 | document.querySelector("#summary").innerHTML = extractSummary(json); 457 | } 458 | 459 | if (document.querySelector("#topics") !== null) { 460 | document.querySelector("#topics").innerHTML = extractTopics(json).join(", "); 461 | } 462 | 463 | language = getLanguageCode(json); 464 | 465 | let track = document.querySelector('#hyperplayer-vtt'); 466 | track.label = language; 467 | track.srcLang = language; 468 | 469 | wordData.forEach((element, index) => { 470 | 471 | let currentWord = punctuatedWords[index]; 472 | wordsInPara++; 473 | 474 | // if there's a gap longer than half a second consider splitting into new para 475 | 476 | if (previousElementEnd !== 0 && (element.start - previousElementEnd) > significantGapInSeconds || wordsInPara > maxWordsInPara){ 477 | let previousWord = punctuatedWords[index-1]; 478 | let previousWordLastChar = previousWord.charAt(previousWord.length-1); 479 | if (previousWordLastChar === "." || previousWordLastChar === "?" || previousWordLastChar === "!") { 480 | hyperTranscript += "\n

\n

\n "; 481 | wordsInPara = 0; 482 | } 483 | } 484 | 485 | // change of speaker or first word 486 | if ((showDiarization === true && index > 0 && element.speaker !== wordData[index-1].speaker) || index === 0) { 487 | let previousWord = punctuatedWords[index-1]; 488 | let previousWordLastChar = null; 489 | 490 | if (index > 0) { 491 | previousWordLastChar = previousWord.charAt(previousWord.length-1); 492 | } 493 | 494 | if (index > 0 && (previousWordLastChar === "." || previousWordLastChar === "?" || previousWordLastChar === "!")) { 495 | hyperTranscript += "\n

\n

\n "; 496 | wordsInPara = 0; 497 | } 498 | hyperTranscript += `[speaker-${element.speaker}] `; 499 | } 500 | 501 | hyperTranscript += `${currentWord} `; 502 | 503 | previousElementEnd = element.end; 504 | }); 505 | 506 | hyperTranscript += "\n

\n
\n
\n "; 507 | 508 | document.querySelector("#hypertranscript").innerHTML = hyperTranscript; 509 | 510 | let showSpeakers = document.querySelector('#show-speakers'); 511 | let speakers = document.querySelectorAll('.speaker'); 512 | 513 | if (showSpeakers.checked === true) { 514 | speakers.forEach((speaker) => { 515 | speaker.style.display = "inline"; 516 | }); 517 | } else { 518 | speakers.forEach((speaker) => { 519 | speaker.style.display = "none"; 520 | }); 521 | } 522 | 523 | console.log("updating download html link"); 524 | document.querySelector('#download-html').setAttribute('href', 'data:text/html,'+encodeURIComponent(hyperTranscript)); 525 | 526 | const initEvent = new CustomEvent('hyperaudioInit'); 527 | document.dispatchEvent(initEvent); 528 | const capEvent = new CustomEvent('hyperaudioGenerateCaptionsFromTranscript'); 529 | document.dispatchEvent(capEvent); 530 | } 531 | 532 | function extractSummary(json) { 533 | let summary = ""; 534 | const summaryData = json.results.channels[0].alternatives[0].summaries; 535 | 536 | summaryData.forEach((element, index) => { 537 | summary += element.summary; 538 | if (index < summaryData.length - 1) { 539 | summary += "\n\n"; 540 | } 541 | }); 542 | 543 | return (summary); 544 | } 545 | 546 | function extractTopics(json) { 547 | let topics = []; 548 | const topicsData = json.results.channels[0].alternatives[0].topics; 549 | 550 | topicsData.forEach(element => { 551 | element.topics.forEach(el => { 552 | topics.push(el.topic); 553 | }); 554 | }); 555 | 556 | return (topics); 557 | } 558 | 559 | function extractLanguage(json) { 560 | let language = json.results.channels[0].detected_language; 561 | return (language); 562 | } 563 | 564 | function populateLanguageDeepgram() { 565 | 566 | const select = document.querySelector('#language'); 567 | select.innerHTML = ""; 568 | 569 | const optionLanguage = { 570 | "English": "en", 571 | "English (United States)": "en-US", 572 | "English (Great Britain)": "en-GB", 573 | "English (Australia)": "en-AU", 574 | "English (India)" : "en-IN", 575 | "English (New Zealand)" : "en-NZ", 576 | "Chinese": "zh", 577 | "Chinese, Simplified Mandarin (China)": "zh-CN", 578 | "Chinese, Traditional Mandarin (Taiwan)": "zh-TW", 579 | "Dutch": "nl", 580 | "French" : "fr", 581 | "French (Canada)" : "fr-CA", 582 | "German" : "de", 583 | "Hindi" : "hi", 584 | "Hindi (Latin Script)" : "hi-Latn", 585 | "Indonesian" : "id", 586 | "Italian": "it", 587 | "Japanese" : "ja", 588 | "Korean" : "ko", 589 | "Polish" : "pl", 590 | "Portuguese": "pt", 591 | "Portuguese (Brazil)" : "pt-BR", 592 | "Portuguese (Portugal)" : "pt-PT", 593 | "Russian" : "ru", 594 | "Spanish" : "es", 595 | "Swedish" : "sv", 596 | "Turkish" : "tr", 597 | "Ukrainian": "uk" 598 | } 599 | 600 | Object.keys(optionLanguage).forEach( language => { 601 | let option = document.createElement("option") 602 | option.value = optionLanguage[language] 603 | option.innerHTML = `${language}` 604 | select.appendChild(option); 605 | } ); 606 | 607 | document.querySelector("#tier").disabled=false; 608 | } 609 | 610 | function populateLanguageWhisper() { 611 | 612 | const select = document.querySelector('#language'); 613 | select.innerHTML = ""; 614 | 615 | const optionLanguage = { 616 | "Auto Detect": "xx", 617 | "English": "en", 618 | "Afrikaans": "af", 619 | "Arabic": "ar", 620 | "Armenian": "hy", 621 | "Azerbaijani": "az", 622 | "Belarusian": "be", 623 | "Bosnian": "bs", 624 | "Bulgarian": "bg", 625 | "Catalan": "ca", 626 | "Chinese": "zh", 627 | "Croatian": "hr", 628 | "Czech": "cs", 629 | "Danish": "da", 630 | "Dutch": "nl", 631 | "Estonian": "et", 632 | "Finnish": "fi", 633 | "French": "fr", 634 | "Galician": "gl", 635 | "German": "de", 636 | "Greek": "el", 637 | "Hebrew": "he", 638 | "Hindi": "hi", 639 | "Hungarian": "hu", 640 | "Icelandic": "is", 641 | "Indonesian": "id", 642 | "Italian": "it", 643 | "Japanese": "ja", 644 | "Kannada": "kn", 645 | "Kazakh": "kk", 646 | "Korean": "ko", 647 | "Latvian": "lv", 648 | "Lithuanian": "lt", 649 | "Macedonian": "mk", 650 | "Malay": "ms", 651 | "Marathi": "mr", 652 | "Maori": "mi", 653 | "Nepali": "ne", 654 | "Norwegian": "no", 655 | "Persian": "fa", 656 | "Polish": "pl", 657 | "Portuguese": "pt", 658 | "Romanian": "ro", 659 | "Russian": "ru", 660 | "Serbian": "sr", 661 | "Slovak": "sk", 662 | "Slovenian": "sl", 663 | "Spanish": "es", 664 | "Swahili": "sw", 665 | "Swedish": "sv", 666 | "Tagalog": "tl", 667 | "Tamil": "ta", 668 | "Thai": "th", 669 | "Turkish": "tr", 670 | "Ukrainian": "uk", 671 | "Urdu": "ur", 672 | "Vietnamese": "vi", 673 | "Welsh": "cy" 674 | }; 675 | 676 | Object.keys(optionLanguage).forEach( language => { 677 | let option = document.createElement("option"); 678 | option.value = optionLanguage[language]; 679 | option.innerHTML = `${language}` 680 | select.appendChild(option); 681 | } ); 682 | 683 | document.querySelector("#tier").disabled=true; 684 | } 685 | 686 | function populateLanguageDeepgramRestricted() { 687 | 688 | const select = document.querySelector('#language'); 689 | select.innerHTML = ""; 690 | 691 | const optionLanguage = { 692 | "English": "en", 693 | "English (United States)": "en-US" 694 | } 695 | 696 | Object.keys(optionLanguage).forEach( language => { 697 | let option = document.createElement("option") 698 | option.value = optionLanguage[language] 699 | option.innerHTML = `${language}` 700 | select.appendChild(option); 701 | } ); 702 | 703 | document.querySelector("#tier").disabled=false; 704 | } 705 | -------------------------------------------------------------------------------- /js/hyperaudio-lite-editor-export.js: -------------------------------------------------------------------------------- 1 | class ExportJson extends HTMLElement { 2 | 3 | constructor() { 4 | super(); 5 | } 6 | 7 | exportJson() { 8 | let hypertranscript = document.getElementById('hypertranscript'); 9 | 10 | if (hypertranscript === null) { 11 | alert("Currently you can only export JSON from the transcript view."); 12 | } else { 13 | // transform in json object with dom elements 14 | let jsonData = htmlToJson(hypertranscript); 15 | jsonData.url = document.querySelector("#hyperplayer").src; 16 | downloadJson(jsonData); 17 | } 18 | } 19 | 20 | connectedCallback() { 21 | //this.innerHTML = ``; 22 | this.innerHTML = `
Export Hyperaudio JSON`; 23 | this.addEventListener('click', this.exportJson); 24 | } 25 | } 26 | 27 | customElements.define('export-json', ExportJson); 28 | 29 | class ImportJson extends HTMLElement { 30 | 31 | constructor() { 32 | super(); 33 | } 34 | 35 | importJson() { 36 | 37 | //import data from json file when click on import button 38 | const fileInput = document.createElement('input'); 39 | fileInput.type = 'file'; 40 | fileInput.accept = 'application/json'; 41 | fileInput.addEventListener('change', (event) => { 42 | const file = event.target.files[0]; 43 | const reader = new FileReader(); 44 | reader.addEventListener('load', (event) => { 45 | const jsonData = JSON.parse(event.target.result); 46 | // transform json object in html 47 | let hypertranscript = document.getElementById('hypertranscript'); 48 | 49 | if (hypertranscript === null) { 50 | alert("Currently you can only import JSON from the Transcript View."); 51 | } else { 52 | hypertranscript.innerHTML = jsonToHtml(jsonData); 53 | // set video url 54 | document.querySelector("#hyperplayer").src = jsonData.url; 55 | } 56 | }); 57 | if (hypertranscript !== null) { 58 | reader.readAsText(file); 59 | document.dispatchEvent(new CustomEvent('hyperaudioInit')); 60 | } 61 | }); 62 | fileInput.click(); 63 | } 64 | 65 | connectedCallback() { 66 | //this.innerHTML = ``; 67 | this.innerHTML = `Import Hyperaudio JSON`; 68 | this.addEventListener('click', this.importJson); 69 | } 70 | } 71 | 72 | customElements.define('import-json', ImportJson); 73 | 74 | class ImportDeepgramJson extends HTMLElement { 75 | 76 | constructor() { 77 | super(); 78 | } 79 | 80 | clearDeepgramJsonMediaUrl(event) { 81 | event.preventDefault(); 82 | document.querySelector('#deepgram-json-media').value = ""; 83 | } 84 | 85 | clearDeepgramJsonFilePicker(event) { 86 | event.preventDefault(); 87 | document.querySelector('#deepgram-json-file').value = ""; 88 | } 89 | 90 | confirmDeepgramJson() { 91 | let player = document.querySelector("#hyperplayer"); 92 | if (document.querySelector('#deepgram-json-file').value == ""){ 93 | player.src = document.querySelector('#deepgram-json-media').value; 94 | } else { 95 | const file = document.querySelector('[name=deepgram-json-file]').files[0]; 96 | // Create a new FileReader instance 97 | const reader = new FileReader(); 98 | reader.readAsArrayBuffer(file); 99 | let blob = null; 100 | 101 | reader.addEventListener('load', () => { 102 | 103 | file.arrayBuffer().then((arrayBuffer) => { 104 | blob = new Blob([new Uint8Array(arrayBuffer)], {type: file.type }); 105 | player.src = URL.createObjectURL(blob); 106 | }); 107 | }); 108 | } 109 | 110 | const file = document.querySelector('[name=deepgram-json]').files[0]; 111 | const reader = new FileReader(); 112 | reader.addEventListener('load', (event) => { 113 | parseData(JSON.parse(event.target.result)); 114 | }); 115 | 116 | reader.readAsText(file); 117 | } 118 | 119 | connectedCallback() { 120 | this.innerHTML = ` 121 |
122 | 123 |
124 | 125 | `; 142 | 143 | document.querySelector('#deepgram-json-file').addEventListener('change',this.clearDeepgramJsonMediaUrl); 144 | document.querySelector('#deepgram-json-media').addEventListener('change',this.clearDeepgramJsonFilePicker); 145 | document.querySelector('#file-import-deepgram-json').addEventListener('click',this.confirmDeepgramJson); 146 | 147 | document.addEventListener('DOMContentLoaded', () => { 148 | const deepgramMediaInput = document.getElementById('deepgram-json-media'); 149 | const deepgramFileInput = document.getElementById('deepgram-json-file'); 150 | 151 | // Function to toggle the disabled state of inputs 152 | function toggleDeepgramInputDisabled() { 153 | if (deepgramMediaInput.value.trim() !== '') { 154 | deepgramFileInput.disabled = true; 155 | } else { 156 | deepgramFileInput.disabled = false; 157 | } 158 | 159 | if (deepgramFileInput.files.length > 0) { 160 | deepgramMediaInput.disabled = true; 161 | } else { 162 | deepgramMediaInput.disabled = false; 163 | } 164 | } 165 | 166 | // Add event listener to deepgram-media to monitor changes 167 | deepgramMediaInput.addEventListener('input', toggleDeepgramInputDisabled); 168 | 169 | // Add event listener to deepgram-file to monitor changes 170 | deepgramFileInput.addEventListener('change', toggleDeepgramInputDisabled); 171 | 172 | // Initial check to set the correct state on page load 173 | toggleDeepgramInputDisabled(); 174 | }); 175 | } 176 | } 177 | 178 | customElements.define('import-deepgram-json', ImportDeepgramJson); 179 | 180 | 181 | class ImportSrt extends HTMLElement { 182 | 183 | constructor() { 184 | super(); 185 | } 186 | 187 | clearSrtMediaUrl(event) { 188 | event.preventDefault(); 189 | document.querySelector('#srt-media').value = ""; 190 | } 191 | 192 | clearSrtFilePicker(event) { 193 | event.preventDefault(); 194 | document.querySelector('#srt-file').value = ""; 195 | } 196 | 197 | confirmSrt() { 198 | let player = document.querySelector("#hyperplayer"); 199 | if (document.querySelector('#srt-file').value == ""){ 200 | console.log("new src ", document.querySelector('#srt-media').value); 201 | player.src = document.querySelector('#srt-media').value; 202 | } else { 203 | const file = document.querySelector('[name=srt-file]').files[0]; 204 | // Create a new FileReader instance 205 | const reader = new FileReader(); 206 | reader.readAsArrayBuffer(file); 207 | let blob = null; 208 | 209 | reader.addEventListener('load', () => { 210 | 211 | file.arrayBuffer().then((arrayBuffer) => { 212 | blob = new Blob([new Uint8Array(arrayBuffer)], {type: file.type }); 213 | player.src = URL.createObjectURL(blob); 214 | }); 215 | }); 216 | } 217 | 218 | const file = document.querySelector('[name=srt]').files[0]; 219 | const reader = new FileReader(); 220 | reader.addEventListener('load', (event) => { 221 | const srtData = event.target.result; 222 | 223 | let hypertranscript = document.getElementById('hypertranscript'); 224 | hypertranscript.innerHTML = srtToHtml(srtData); 225 | 226 | const vttData = convertSrtToWebVtt(srtData); 227 | // Create a Blob object with the WebVTT data 228 | const blob = new Blob([vttData], { type: "text/vtt" }); 229 | // Generate a URL for the Blob 230 | const vttUrl = URL.createObjectURL(blob); 231 | document.querySelector('#hyperplayer-vtt').src = vttUrl; 232 | 233 | // Preserve original format 234 | updateCaptionsFromTranscript = false; 235 | populateCaptionEditorFromVtt(vttData); 236 | //captionCache = vttData; 237 | 238 | document.dispatchEvent(new CustomEvent('hyperaudioInit')); 239 | }); 240 | 241 | reader.readAsText(file); 242 | 243 | } 244 | 245 | 246 | connectedCallback() { 247 | this.innerHTML = ` 248 |
249 | 250 |
251 | 252 | `; 269 | 270 | document.querySelector('#srt').addEventListener('change',this.clearSrtMediaUrl); 271 | document.querySelector('#srt-media').addEventListener('change',this.clearSrtFilePicker); 272 | document.querySelector('#file-import-srt').addEventListener('click',this.confirmSrt); 273 | 274 | document.addEventListener('DOMContentLoaded', () => { 275 | const srtMediaInput = document.getElementById('srt-media'); 276 | const srtFileInput = document.getElementById('srt-file'); 277 | 278 | // Function to toggle the disabled state of inputs 279 | function toggleInputDisabled() { 280 | if (srtMediaInput.value.trim() !== '') { 281 | srtFileInput.disabled = true; 282 | } else { 283 | srtFileInput.disabled = false; 284 | } 285 | 286 | if (srtFileInput.files.length > 0) { 287 | srtMediaInput.disabled = true; 288 | } else { 289 | srtMediaInput.disabled = false; 290 | } 291 | } 292 | 293 | // Add event listener to srt-media to monitor changes 294 | srtMediaInput.addEventListener('input', toggleInputDisabled); 295 | 296 | // Add event listener to srt-file to monitor changes 297 | srtFileInput.addEventListener('change', toggleInputDisabled); 298 | 299 | // Initial check to set the correct state on page load 300 | toggleInputDisabled(); 301 | }); 302 | } 303 | } 304 | 305 | customElements.define('import-srt', ImportSrt); 306 | 307 | class ImportVtt extends HTMLElement { 308 | 309 | constructor() { 310 | super(); 311 | } 312 | 313 | clearVttMediaUrl(event) { 314 | event.preventDefault(); 315 | document.querySelector('#vtt-media').value = ""; 316 | } 317 | 318 | clearVttFilePicker(event) { 319 | event.preventDefault(); 320 | document.querySelector('#vtt-file').value = ""; 321 | } 322 | 323 | confirmVtt() { 324 | let player = document.querySelector("#hyperplayer"); 325 | if (document.querySelector('#vtt-file').value == ""){ 326 | console.log("new src ", document.querySelector('#vtt-media').value); 327 | player.src = document.querySelector('#vtt-media').value; 328 | } else { 329 | const file = document.querySelector('[name=vtt-file]').files[0]; 330 | // Create a new FileReader instance 331 | const reader = new FileReader(); 332 | reader.readAsArrayBuffer(file); 333 | let blob = null; 334 | 335 | reader.addEventListener('load', () => { 336 | 337 | file.arrayBuffer().then((arrayBuffer) => { 338 | blob = new Blob([new Uint8Array(arrayBuffer)], {type: file.type }); 339 | player.src = URL.createObjectURL(blob); 340 | }); 341 | }); 342 | } 343 | 344 | const file = document.querySelector('[name=vtt]').files[0]; 345 | const reader = new FileReader(); 346 | reader.addEventListener('load', (event) => { 347 | const vttData = event.target.result; 348 | 349 | let hypertranscript = document.getElementById('hypertranscript'); 350 | hypertranscript.innerHTML = vttToHtml(vttData); 351 | 352 | const blob = new Blob([vttData], { type: "text/vtt" }); 353 | // Generate a URL for the Blob 354 | const vttUrl = URL.createObjectURL(blob); 355 | document.querySelector('#hyperplayer-vtt').src = vttUrl; 356 | 357 | // Preserve original format 358 | updateCaptionsFromTranscript = false; 359 | populateCaptionEditorFromVtt(vttData); 360 | //captionCache = vttData; 361 | 362 | document.dispatchEvent(new CustomEvent('hyperaudioInit')); 363 | }); 364 | 365 | reader.readAsText(file); 366 | 367 | } 368 | 369 | 370 | connectedCallback() { 371 | this.innerHTML = ` 372 |
373 | 374 |
375 | 376 | `; 393 | 394 | document.querySelector('#vtt').addEventListener('change',this.clearVttMediaUrl); 395 | document.querySelector('#vtt-media').addEventListener('change',this.clearVttFilePicker); 396 | document.querySelector('#file-import-vtt').addEventListener('click',this.confirmVtt); 397 | 398 | document.addEventListener('DOMContentLoaded', () => { 399 | const vttMediaInput = document.getElementById('vtt-media'); 400 | const vttFileInput = document.getElementById('vtt-file'); 401 | 402 | // Function to toggle the disabled state of inputs 403 | function toggleInputDisabled() { 404 | if (vttMediaInput.value.trim() !== '') { 405 | vttFileInput.disabled = true; 406 | } else { 407 | vttFileInput.disabled = false; 408 | } 409 | 410 | if (vttFileInput.files.length > 0) { 411 | vttMediaInput.disabled = true; 412 | } else { 413 | vttMediaInput.disabled = false; 414 | } 415 | } 416 | 417 | // Add event listener to srt-media to monitor changes 418 | vttMediaInput.addEventListener('input', toggleInputDisabled); 419 | 420 | // Add event listener to srt-file to monitor changes 421 | vttFileInput.addEventListener('change', toggleInputDisabled); 422 | 423 | // Initial check to set the correct state on page load 424 | toggleInputDisabled(); 425 | }); 426 | } 427 | } 428 | 429 | customElements.define('import-vtt', ImportVtt); 430 | 431 | function downloadJson(jsonData) { 432 | // download json file 433 | let dataStr = 'data:text/json;charset=utf-8,' + encodeURIComponent(JSON.stringify(jsonData)); 434 | //start download 435 | let downloadAnchorNode = document.createElement('a'); 436 | downloadAnchorNode.setAttribute('href', dataStr); 437 | downloadAnchorNode.setAttribute('download', 'hyperaudio-lite.json'); 438 | document.body.appendChild(downloadAnchorNode); // required for firefox 439 | downloadAnchorNode.click(); 440 | downloadAnchorNode.remove(); 441 | } 442 | 443 | /** 444 | * Converts SRT subtitle format to WebVTT format 445 | * @param {string} srtContent - The SRT content as a string 446 | * @returns {string} - The converted WebVTT content 447 | */ 448 | function convertSrtToWebVtt(srtContent) { 449 | // First, normalize line endings to ensure consistent processing across platforms 450 | const normalizedContent = srtContent.replace(/\r\n|\r/g, '\n'); 451 | 452 | // WebVTT files must start with "WEBVTT" followed by a blank line 453 | let webVttContent = "WEBVTT\n\n"; 454 | 455 | // Split the content into subtitle blocks (separated by blank lines) 456 | const subtitleBlocks = normalizedContent.split(/\n\s*\n/); 457 | 458 | for (const block of subtitleBlocks) { 459 | if (!block.trim()) continue; 460 | 461 | // Split each block into lines 462 | const lines = block.split('\n'); 463 | 464 | // Skip the subtitle number (first line in SRT) 465 | // If the block doesn't have at least 2 lines, skip it 466 | if (lines.length < 2) continue; 467 | 468 | // Get the timestamp line (second line in SRT) 469 | const timestampLine = lines[1]; 470 | 471 | // Convert SRT timestamp format (00:00:00,000) to WebVTT format (00:00:00.000) 472 | const webVttTimestamp = timestampLine.replace(/,/g, '.'); 473 | 474 | // Add the timestamp line 475 | webVttContent += webVttTimestamp + '\n'; 476 | 477 | // Add the subtitle text (all lines after the timestamp) 478 | const subtitleText = lines.slice(2).join('\n'); 479 | webVttContent += subtitleText + '\n\n'; 480 | } 481 | 482 | return webVttContent; 483 | } 484 | 485 | // Convert Hypertranscript to JSON 486 | function htmlToJson(html) { 487 | const article = html.querySelector('article'); 488 | 489 | // Create an empty object to store the JSON data 490 | const jsonData = {}; 491 | 492 | // Add the
element data to the JSON object 493 | jsonData.article = {}; 494 | 495 | // Get the
element 496 | const section = article.querySelector('section'); 497 | 498 | // Add the
element data to the JSON object 499 | jsonData.article.section = {}; 500 | 501 | // Get the

element 502 | const paragraphs = section.querySelectorAll('p'); 503 | 504 | // Add the

element data to the JSON object 505 | jsonData.article.section.paragraphs = []; 506 | 507 | // Iterate through each

element 508 | for (const paragraph of paragraphs) { 509 | // Create an object to store the

element data 510 | const paragraphData = {}; 511 | // Get all the elements within the

element 512 | const spans = paragraph.querySelectorAll('span'); 513 | 514 | // Add the elements data to the JSON object 515 | paragraphData.spans = []; 516 | 517 | // Iterate through each element 518 | for (const span of spans) { 519 | // Create an object to store the element data 520 | const spanData = {}; 521 | 522 | // Get the "data-m" attribute value 523 | spanData.m = span.getAttribute('data-m'); 524 | 525 | // Get the "data-d" attribute value 526 | spanData.d = span.getAttribute('data-d'); 527 | 528 | // Get the class attribute value 529 | spanData.class = span.getAttribute('class'); 530 | 531 | // Get the text content of the element 532 | spanData.text = span.textContent; 533 | 534 | // Add the element data to the JSON object 535 | paragraphData.spans.push(spanData); 536 | } 537 | jsonData.article.section.paragraphs.push(paragraphData); 538 | } 539 | // Return the JSON object 540 | return jsonData; 541 | } 542 | 543 | 544 | // Convert JSON to Hypertranscript HTML 545 | function jsonToHtml(jsonData) { 546 | // Create an empty

element 547 | const div = document.createElement('div'); 548 | 549 | const article = document.createElement('article'); 550 | 551 | // Create an empty
element 552 | const section = document.createElement('section'); 553 | 554 | // Add the
element to the
element 555 | article.appendChild(section); 556 | 557 | // Get the

elements data from the JSON object 558 | const paragraphs = jsonData.article.section.paragraphs; 559 | 560 | // Iterate through each

element 561 | for (const paragraph of paragraphs) { 562 | // Create an empty

element 563 | const p = document.createElement('p'); 564 | 565 | // Add the

element to the

element 566 | section.appendChild(p); 567 | 568 | // Get the elements data from the JSON object 569 | const spans = paragraph.spans; 570 | 571 | // Iterate through each element 572 | for (const span of spans) { 573 | // Create an empty element 574 | const spanElement = document.createElement('span'); 575 | 576 | // Set the "data-m" attribute value 577 | spanElement.setAttribute('data-m', span.m); 578 | 579 | // Set the "data-d" attribute value 580 | spanElement.setAttribute('data-d', span.d); 581 | 582 | // Set the class attribute value 583 | spanElement.setAttribute('class', span.class); 584 | 585 | // Set the text content of the element 586 | spanElement.textContent = span.text; 587 | 588 | // Add the element to the

element 589 | p.appendChild(spanElement); 590 | } 591 | } 592 | 593 | div.appendChild(article); 594 | // Return the

element 595 | 596 | return div.innerHTML; 597 | } 598 | 599 | function srtToHtml(data) { 600 | let i = 0, 601 | len = 0, 602 | idx = 0, 603 | lines, 604 | time, 605 | text, 606 | sub; 607 | 608 | // Simple function to convert HH:MM:SS,MMM or HH:MM:SS.MMM to SS.MMM 609 | // Assume valid, returns 0 on error 610 | 611 | let toSeconds = function(t_in) { 612 | let t = t_in.split(':'); 613 | 614 | try { 615 | let s = t[2].split(','); 616 | 617 | // Just in case a . is decimal seperator 618 | if (s.length === 1) { 619 | s = t[2].split('.'); 620 | } 621 | 622 | return ( 623 | parseFloat(t[0], 10) * 3600 + 624 | parseFloat(t[1], 10) * 60 + 625 | parseFloat(s[0], 10) + 626 | parseFloat(s[1], 10) / 1000 627 | ); 628 | } catch (e) { 629 | return 0; 630 | } 631 | }; 632 | 633 | let paraSplitTime = 1.5; 634 | let paraPunct = true; 635 | let outputString = '

'; 636 | let lineBreaks = false; 637 | let ltime = 0; 638 | let ltext; 639 | 640 | // Here is where the magic happens 641 | // Split on line breaks 642 | lines = data.split(/(?:\r\n|\r|\n)/gm); 643 | len = lines.length; 644 | 645 | for (i = 0; i < len; i++) { 646 | sub = {}; 647 | text = []; 648 | 649 | sub.id = parseInt(lines[i++], 10); 650 | 651 | // Split on '-->' delimiter, trimming spaces as well 652 | 653 | try { 654 | time = lines[i++].split(/[\t ]*-->[\t ]*/); 655 | } catch (e) { 656 | console.log('Warning. Possible issue on line ' + i + ": '" + lines[i] + "'."); 657 | break; 658 | } 659 | 660 | sub.start = toSeconds(time[0]); 661 | 662 | // So as to trim positioning information from end 663 | if (!time[1]) { 664 | alert('Warning. Issue on line ' + i + ": '" + lines[i] + "'."); 665 | return; 666 | } 667 | 668 | idx = time[1].indexOf(' '); 669 | if (idx !== -1) { 670 | time[1] = time[1].substr(0, idx); 671 | } 672 | sub.end = toSeconds(time[1]); 673 | 674 | // Build single line of text from multi-line subtitle in file 675 | while (i < len && lines[i]) { 676 | text.push(lines[i++]); 677 | } 678 | 679 | // Join into 1 line, SSA-style linebreaks 680 | // Strip out other SSA-style tags 681 | sub.text = text.join('\\N').replace(/\{(\[\w]+\(?([\w\d]+,?)+\)?)+\}/gi, ''); 682 | 683 | // Escape HTML entities 684 | sub.text = sub.text.replace(//g, '>'); 685 | 686 | // Unescape great than and less than when it makes a valid html tag of a supported style (font, b, u, s, i) 687 | // Modified version of regex from Phil Haack's blog: http://haacked.com/archive/2004/10/25/usingregularexpressionstomatchhtml.aspx 688 | // Later modified by kev: http://kevin.deldycke.com/2007/03/ultimate-regular-expression-for-html-tag-parsing-with-php/ 689 | sub.text = sub.text.replace( 690 | /<(\/?(font|b|u|i|s))((\s+(\w|\w[\w\-]*\w)(\s*=\s*(?:\".*?\"|'.*?'|[^'\">\s]+))?)+\s*|\s*)(\/?)>/gi, 691 | '<$1$3$7>' 692 | ); 693 | //sub.text = sub.text.replace( /\\N/gi, "
" ); 694 | sub.text = sub.text.replace(/\\N/gi, ' '); 695 | 696 | let splitMode = 0; 697 | 698 | let wordLengthSplit = true; //$('#word-length').prop('checked'); 699 | 700 | // enhancements to take account of word length 701 | 702 | let swords = sub.text.split(' '); 703 | let sduration = sub.end - sub.start; 704 | let stimeStep = sduration / swords.length; 705 | 706 | // determine length of words 707 | 708 | let swordLengths = []; 709 | 710 | let totalLetters = 0; 711 | for (let si = 0, sl = swords.length; si < sl; ++si) { 712 | totalLetters = totalLetters + swords[si].length; 713 | swordLengths[si] = swords[si].length; 714 | } 715 | 716 | let letterTime = sduration / totalLetters; 717 | let wordStart = 0; 718 | 719 | for (let si = 0, sl = swords.length; si < sl; ++si) { 720 | let wordTime = swordLengths[si] * letterTime; 721 | let stime; 722 | if (wordLengthSplit) { 723 | stime = Math.round((sub.start + si * stimeStep) * 1000); 724 | } else { 725 | stime = Math.round((wordStart + sub.start) * 1000); 726 | } 727 | 728 | wordStart = wordStart + wordTime; 729 | let stext = swords[si]; 730 | 731 | if (stime - ltime > paraSplitTime * 1000 && paraSplitTime > 0) { 732 | 733 | let punctPresent = 734 | ltext && (ltext.indexOf('.') > 0 || ltext.indexOf('?') > 0 || ltext.indexOf('!') > 0); 735 | if (!paraPunct || (paraPunct && punctPresent)) { 736 | outputString += '

'; 737 | } 738 | } 739 | 740 | outputString += '' + stext + ' '; 741 | 742 | ltime = stime; 743 | ltext = stext; 744 | 745 | if (lineBreaks) outputString = outputString + '\n'; 746 | } 747 | } 748 | return outputString + '

'; 749 | } 750 | 751 | /** 752 | * Converts WebVTT subtitle format to HTML for the hypertranscript 753 | * @param {string} data - The WebVTT content as a string 754 | * @returns {string} - The converted HTML content 755 | */ 756 | function vttToHtml(data) { 757 | let i = 0, 758 | len = 0, 759 | lines, 760 | time, 761 | text, 762 | sub; 763 | 764 | // Simple function to convert HH:MM:SS.MMM to seconds 765 | // Assume valid, returns 0 on error 766 | let toSeconds = function(t_in) { 767 | let t = t_in.split(':'); 768 | 769 | try { 770 | let s = t[2].split('.'); 771 | 772 | // Just in case a , is decimal separator 773 | if (s.length === 1) { 774 | s = t[2].split(','); 775 | } 776 | 777 | return ( 778 | parseFloat(t[0], 10) * 3600 + 779 | parseFloat(t[1], 10) * 60 + 780 | parseFloat(s[0], 10) + 781 | parseFloat(s[1], 10) / 1000 782 | ); 783 | } catch (e) { 784 | return 0; 785 | } 786 | }; 787 | 788 | let paraSplitTime = 1.5; 789 | let paraPunct = true; 790 | let outputString = '

'; 791 | let lineBreaks = false; 792 | let ltime = 0; 793 | let ltext; 794 | 795 | // Split on line breaks 796 | lines = data.split(/(?:\r\n|\r|\n)/gm); 797 | len = lines.length; 798 | 799 | // Skip the WEBVTT header line 800 | let startLine = 0; 801 | if (lines[0].indexOf('WEBVTT') === 0) { 802 | startLine = 1; 803 | 804 | // Skip any header metadata lines 805 | while (startLine < len && lines[startLine].trim() !== '') { 806 | startLine++; 807 | } 808 | 809 | // Skip the blank line after the header 810 | startLine++; 811 | } 812 | 813 | for (i = startLine; i < len; i++) { 814 | sub = {}; 815 | text = []; 816 | 817 | // Skip empty lines 818 | if (!lines[i].trim()) { 819 | continue; 820 | } 821 | 822 | // Check if the line is a cue identifier (optional in WebVTT) 823 | if (lines[i].indexOf('-->') === -1) { 824 | // This might be a cue identifier, skip to the next line 825 | i++; 826 | 827 | // Skip if we've reached the end 828 | if (i >= len) break; 829 | } 830 | 831 | // Parse the timestamp line 832 | if (lines[i].indexOf('-->') !== -1) { 833 | time = lines[i].split(/[\t ]*-->[\t ]*/); 834 | 835 | sub.start = toSeconds(time[0]); 836 | 837 | // Extract end time, removing any cue settings 838 | let endTimeStr = time[1].split(/[\t ]/)[0]; 839 | sub.end = toSeconds(endTimeStr); 840 | 841 | // Move to the next line, which should be the start of the text 842 | i++; 843 | 844 | // Collect all lines of text until we hit an empty line 845 | while (i < len && lines[i].trim() !== '') { 846 | text.push(lines[i]); 847 | i++; 848 | } 849 | 850 | // Join the text lines 851 | sub.text = text.join(' ').replace(/\{(\[\w]+\(?([\w\d]+,?)+\)?)+\}/gi, ''); 852 | 853 | // Escape HTML entities 854 | sub.text = sub.text.replace(//g, '>'); 855 | 856 | // Unescape specific HTML tags 857 | sub.text = sub.text.replace( 858 | /<(\/?(font|b|u|i|s))((\s+(\w|\w[\w\-]*\w)(\s*=\s*(?:\".*?\"|'.*?'|[^'\">\s]+))?)+\s*|\s*)(\/?)>/gi, 859 | '<$1$3$7>' 860 | ); 861 | 862 | // Split into words for timestamping 863 | let swords = sub.text.split(' '); 864 | let sduration = sub.end - sub.start; 865 | let stimeStep = sduration / swords.length; 866 | 867 | // Determine length of words 868 | let swordLengths = []; 869 | let totalLetters = 0; 870 | 871 | for (let si = 0, sl = swords.length; si < sl; ++si) { 872 | totalLetters = totalLetters + swords[si].length; 873 | swordLengths[si] = swords[si].length; 874 | } 875 | 876 | let letterTime = sduration / totalLetters; 877 | let wordStart = 0; 878 | let wordLengthSplit = true; 879 | 880 | for (let si = 0, sl = swords.length; si < sl; ++si) { 881 | let wordTime = swordLengths[si] * letterTime; 882 | let stime; 883 | 884 | if (wordLengthSplit) { 885 | stime = Math.round((sub.start + si * stimeStep) * 1000); 886 | } else { 887 | stime = Math.round((wordStart + sub.start) * 1000); 888 | } 889 | 890 | wordStart = wordStart + wordTime; 891 | let stext = swords[si]; 892 | 893 | if (stime - ltime > paraSplitTime * 1000 && paraSplitTime > 0) { 894 | let punctPresent = 895 | ltext && (ltext.indexOf('.') > 0 || ltext.indexOf('?') > 0 || ltext.indexOf('!') > 0); 896 | 897 | if (!paraPunct || (paraPunct && punctPresent)) { 898 | outputString += '

'; 899 | } 900 | } 901 | 902 | outputString += '' + stext + ' '; 903 | 904 | ltime = stime; 905 | ltext = stext; 906 | 907 | if (lineBreaks) outputString = outputString + '\n'; 908 | } 909 | } 910 | } 911 | 912 | return outputString + '

'; 913 | } -------------------------------------------------------------------------------- /js/hyperaudio-lite-editor-storage.js: -------------------------------------------------------------------------------- 1 | /* 2 | * HyperTranscriptStorage class 3 | * @param {string} hypertranscript - the html of the hypertranscript 4 | * @param {string} video - the url of the video 5 | * @param {string} summary - the text of the summary 6 | * @param {array} topics - an array of topics 7 | * @param {string} captions - VTT format 8 | * @return {void} 9 | */ 10 | class HyperTranscriptStorage { 11 | constructor(hypertranscript, video, summary, topics, captions, meta) { 12 | this.hypertranscript = hypertranscript; 13 | this.video = video; 14 | this.summary = summary; 15 | this.topics = topics; 16 | this.captions = captions; 17 | this.meta = meta; 18 | } 19 | } 20 | 21 | // We should move these from global scope 22 | const fileExtension = ".hyperaudio"; 23 | let lastFilename = null; 24 | 25 | /* 26 | * Render the HyperTranscript in the DOM 27 | * @return {void} 28 | */ 29 | function renderTranscript( 30 | hypertranscriptstorage, 31 | key, 32 | hypertranscriptDomId = 'hypertranscript', 33 | videoDomId = 'hyperplayer', 34 | vttId = 'hyperplayer-vtt', 35 | hypertranscriptHolder = '.transcript-holder', 36 | ) { 37 | let hypertranscriptElement = document.getElementById(hypertranscriptDomId); 38 | 39 | if (hypertranscriptElement) { 40 | hypertranscriptElement.innerHTML = hypertranscriptstorage['hypertranscript']; 41 | } else { 42 | transcriptCache.innerHTML = ""; 43 | //caption page active, put it in the cache 44 | transcriptCache.innerHTML = hypertranscriptstorage['hypertranscript']; 45 | 46 | hypertranscriptElement = transcriptCache; 47 | document.querySelectorAll(hypertranscriptHolder)[0].innerHTML = hypertranscriptElement.innerHTML; 48 | } 49 | 50 | // check to see if file is local 51 | if (hypertranscriptstorage['video'].startsWith("http") === true) { 52 | document.getElementById(videoDomId).src = hypertranscriptstorage['video']; 53 | } else { 54 | //load from indexedDB 55 | let databaseName = "hyperaudioMedia"; 56 | let objectStoreName = "media"; 57 | getMedia(databaseName, objectStoreName, key); 58 | } 59 | 60 | document.getElementById("summary").innerHTML = hypertranscriptstorage['summary']; 61 | document.getElementById("topics").innerHTML = getTopicsString(hypertranscriptstorage['topics']); 62 | 63 | // backward compatibility – check that captions exist, if not generate 64 | 65 | if (hypertranscriptstorage['captions'] === undefined) { //backward compatibility for transcripts without captions 66 | const capEvent = new CustomEvent('hyperaudioGenerateCaptionsFromTranscript'); 67 | document.dispatchEvent(capEvent); 68 | } else { 69 | // stop caption.js inserting VTT upon insertion of new video 70 | 71 | document.getElementById(vttId).src = hypertranscriptstorage['captions']; 72 | //remove data:text/vtt, and decode 73 | let plainVtt = decodeURIComponent(hypertranscriptstorage['captions'].split(',')[1]); 74 | 75 | if (hypertranscriptstorage['meta'] !== undefined && hypertranscriptstorage['meta'].updateCaptionsFromTranscript !== undefined) { 76 | updateCaptionsFromTranscript = hypertranscriptstorage['meta'].updateCaptionsFromTranscript; 77 | } else { 78 | updateCaptionsFromTranscript = true; 79 | } 80 | 81 | //console.log(plainVtt); 82 | 83 | captionCache = null; 84 | 85 | populateCaptionEditorFromVtt(plainVtt); 86 | } 87 | 88 | let hypertranscript = ""; 89 | if (hypertranscriptElement && document.querySelector("#hypertranscript")) { 90 | hypertranscript = document.querySelector("#hypertranscript").innerHTML.replace(/ class=".*?"/g, ''); 91 | } else { 92 | //grab it from the cache 93 | hypertranscript = transcriptCache.innerHTML.replace(/ class=".*?"/g, ''); 94 | } 95 | 96 | document.querySelector('#download-html').setAttribute('href', 'data:text/html,'+encodeURIComponent(hypertranscript)); 97 | 98 | const itDownloadEvent = new CustomEvent('hyperaudioTranscriptLoaded'); 99 | document.dispatchEvent(itDownloadEvent); 100 | 101 | //maybe better called using hyperaudioInit event? 102 | if (captionMode !== true) { 103 | hyperaudio(); 104 | } else { 105 | transcriptRequiresInit = true; 106 | } 107 | 108 | } 109 | 110 | function getLocalStorageSaveFilename(url){ 111 | let filename = null; 112 | 113 | if (lastFilename === null) { 114 | //by default just the media filename 115 | filename = url.substring(url.lastIndexOf("/")+1); 116 | lastFilename = filename; 117 | } else { 118 | // if it's been saved before this session, use the last filename 119 | filename = lastFilename; 120 | } 121 | 122 | return filename; 123 | } 124 | 125 | function getTopicsString(topics) { 126 | let topicsString = ""; 127 | if (topics && topics !== "undefined" && Object.keys(topics).length > 0) { 128 | topicsString = topics.join(", "); 129 | } 130 | return topicsString; 131 | } 132 | 133 | /*******************************************************/ 134 | /* IndexedDB for more permanent storage of local media */ 135 | /*******************************************************/ 136 | 137 | function getMedia(databaseName, objectStoreName, id) { 138 | 139 | let openRequest = indexedDB.open(databaseName, 1); 140 | openRequest.onsuccess = function() { 141 | let db = openRequest.result; 142 | let transaction = db.transaction(objectStoreName, "readonly"); 143 | let videosStore = transaction.objectStore(objectStoreName); 144 | let getRequest = videosStore.get(id); 145 | 146 | getRequest.onerror = function() { 147 | console.error("Error retrieving media:", getRequest.error); 148 | } 149 | 150 | getRequest.onsuccess = function() { 151 | 152 | const base64String = getRequest.result; // Base64 string 153 | 154 | /* The following commented lines should work (but don't) for a more elegant solution */ 155 | /*const binaryString = atob(base64String.split(',')[1]); // Binary data string 156 | const blob = new Blob([binaryString], { type: 'audio/mpeg' }); // Create a BLOB object 157 | let videoURL = URL.createObjectURL(blob); 158 | document.querySelector("#hyperplayer").src = videoURL;*/ 159 | 160 | document.querySelector("#hyperplayer").src = base64String; 161 | } 162 | } 163 | } 164 | 165 | function saveVideoFromBlobURL(filename, blobData, databaseName, objectStoreName) { 166 | 167 | // Open a connection to IndexedDB 168 | let openRequest = indexedDB.open(databaseName, 1); 169 | 170 | openRequest.onupgradeneeded = function() { 171 | let db = openRequest.result; 172 | if (!db.objectStoreNames.contains(objectStoreName)) { 173 | db.createObjectStore(objectStoreName); 174 | } 175 | } 176 | 177 | openRequest.onerror = function() { 178 | console.error("Error opening the database", openRequest.error); 179 | } 180 | 181 | openRequest.onsuccess = function() { 182 | let db = openRequest.result; 183 | 184 | // Save the video using the provided filename as the key 185 | let transaction = db.transaction(objectStoreName, "readwrite"); 186 | let videosStore = transaction.objectStore(objectStoreName); 187 | let request = videosStore.put(blobData, filename); 188 | 189 | request.onerror = function() { 190 | console.error("Error saving the video", request.error); 191 | } 192 | 193 | request.onsuccess = function() { 194 | console.log("Video saved successfully!"); 195 | } 196 | } 197 | } 198 | 199 | function initializeDatabase(database, objectStoreName) { 200 | return new Promise((resolve, reject) => { 201 | let openRequest = indexedDB.open(database, 1); 202 | 203 | openRequest.onupgradeneeded = function() { 204 | let db = openRequest.result; 205 | if (!db.objectStoreNames.contains(objectStoreName)) { 206 | db.createObjectStore(objectStoreName); 207 | } 208 | } 209 | 210 | openRequest.onerror = function() { 211 | console.error("Error opening the database", openRequest.error); 212 | reject(openRequest.error); 213 | } 214 | 215 | openRequest.onsuccess = function() { 216 | resolve(); 217 | } 218 | }); 219 | } 220 | 221 | 222 | /* 223 | * Save the current HyperTranscript in the local storage 224 | * @param {string} filename - the name of the transcript file 225 | * @param {string} hypertranscriptDomId - the id of the hypertranscript dom element 226 | * @param {string} videoDomId - the id of the video dom element 227 | * @return {void} 228 | */ 229 | 230 | function saveHyperTranscriptToLocalStorage( 231 | filename, 232 | hypertranscriptDomId = 'hypertranscript', 233 | videoDomId = 'hyperplayer', 234 | vttId = 'hyperplayer-vtt', 235 | storage = window.localStorage 236 | ) { 237 | let hypertranscriptElement = document.getElementById(hypertranscriptDomId); 238 | let hypertranscript = ""; 239 | if (hypertranscriptElement) { 240 | hypertranscript = hypertranscriptElement.innerHTML; 241 | } else { 242 | //must be in the cache 243 | hypertranscript = transcriptCache.innerHTML; 244 | } 245 | 246 | 247 | let video = document.getElementById(videoDomId).src; 248 | 249 | // if media url begins with blob it means it's locally cached only for the session 250 | // we need to save the media to indexdb so that we can retrieve outside the session 251 | 252 | if (video.startsWith("blob:") === true) { 253 | let objectStoreName = "media"; 254 | let databaseName = "hyperaudioMedia"; 255 | initializeDatabase(databaseName, objectStoreName) 256 | .then(() => { 257 | let blobURL = video; 258 | 259 | fetch(blobURL) 260 | .then(response => response.blob()) 261 | .then(videoBlob => { 262 | const reader = new FileReader(); 263 | let blobData = "not defined"; 264 | reader.onloadend = function() { 265 | blobData = reader.result; 266 | saveVideoFromBlobURL(filename, blobData, databaseName, objectStoreName); 267 | } 268 | reader.readAsDataURL(videoBlob); 269 | }) 270 | .catch(error => { 271 | console.error("Error fetching the video from the blob URL:", error); 272 | }); 273 | }) 274 | .catch(error => { 275 | console.error("Error initializing the database:", error); 276 | }); 277 | } 278 | 279 | let summary = document.getElementById("summary").innerHTML; 280 | let topics = document.getElementById("topics").innerHTML.split(", "); 281 | let captions = document.getElementById(vttId).src; 282 | let meta = {"updateCaptionsFromTranscript": updateCaptionsFromTranscript}; 283 | let hypertranscriptstorage = new HyperTranscriptStorage(hypertranscript, video, summary, topics, captions, meta); 284 | 285 | 286 | try { 287 | storage.setItem(filename + fileExtension, JSON.stringify(hypertranscriptstorage)); 288 | } catch (error) { 289 | if (error.name === 'QuotaExceededError') { 290 | console.error('Storage quota exceeded. Unable to save transcript:', error.message); 291 | // You could add user notification here 292 | alert('Local Storage full - please clear some space to save new transcripts'); 293 | } else { 294 | console.error('Error saving transcript:', error); 295 | } 296 | } 297 | } 298 | 299 | function loadLocalStorageOptions(storage = window.localStorage) { 300 | 301 | let fileSelect = document.querySelector("#load-localstorage-filename"); 302 | let filePicker = document.querySelector("#file-picker"); 303 | 304 | fileSelect.innerHTML = ''; 305 | filePicker.innerHTML = ""; 306 | 307 | for (let i = 0; i < storage.length; i++) { 308 | if (storage.key(i).indexOf(fileExtension) > 0) { 309 | let filename = storage.key(i).substring(0,storage.key(i).lastIndexOf(fileExtension)); 310 | fileSelect.insertAdjacentHTML("beforeend", ``); 311 | filePicker.insertAdjacentHTML("beforeend", `
  • ${filename}
  • `); 312 | } 313 | } 314 | 315 | setFileSelectListeners(); 316 | 317 | if (storage.length === 0) { 318 | filePicker.insertAdjacentHTML("beforeend", `
  • No files saved.
  • `); 319 | } 320 | } 321 | 322 | function setFileSelectListeners() { 323 | let files = document.querySelectorAll('.file-item'); 324 | 325 | files.forEach(file => { 326 | file.removeEventListener('click', fileSelectHandleClick); 327 | file.addEventListener('click', fileSelectHandleClick); 328 | file.removeEventListener('mouseover', fileSelectHandleHover); 329 | file.addEventListener('mouseover', fileSelectHandleHover); 330 | }); 331 | } 332 | 333 | function fileSelectHandleClick(event) { 334 | loadHyperTranscriptFromLocalStorage(event.target.getAttribute("data-index")); 335 | 336 | let files = document.querySelectorAll('.file-item'); 337 | 338 | files.forEach(file => { 339 | file.classList.remove("active"); 340 | }); 341 | 342 | event.target.classList.add("active"); 343 | event.preventDefault(); 344 | return false; 345 | } 346 | 347 | function fileSelectHandleHover(event) { 348 | loadSummaryFromLocalStorage(event.target.getAttribute("data-index"), event.target); 349 | event.preventDefault(); 350 | return false; 351 | } 352 | 353 | function loadHyperTranscriptFromLocalStorage(fileindex, storage = window.localStorage){ 354 | let hypertranscriptstorage = JSON.parse(storage.getItem(storage.key(fileindex))); 355 | 356 | if (hypertranscriptstorage) { 357 | 358 | lastFilename = storage.key(fileindex).substring(0,storage.key(fileindex).lastIndexOf(fileExtension)); 359 | renderTranscript(hypertranscriptstorage, lastFilename); 360 | 361 | document.querySelector('#save-localstorage-filename').value = lastFilename; 362 | } 363 | } 364 | 365 | function loadSummaryFromLocalStorage(fileindex, target, storage = window.localStorage){ 366 | 367 | let hypertranscriptstorage = JSON.parse(storage.getItem(storage.key(fileindex))); 368 | 369 | if (hypertranscriptstorage) { 370 | target.setAttribute("title", hypertranscriptstorage.summary + "\n\nTopics: " + getTopicsString(hypertranscriptstorage.topics)); 371 | } 372 | } -------------------------------------------------------------------------------- /js/hyperaudio-lite-editor-whisper.js: -------------------------------------------------------------------------------- 1 | /*! (C) The Hyperaudio Project. MIT @license: en.wikipedia.org/wiki/MIT_License. */ 2 | /*! Version 0.0.6 (caption editor patch) */ 3 | 4 | class WhisperService extends HTMLElement { 5 | 6 | constructor() { 7 | super(); 8 | } 9 | 10 | connectedCallback() { 11 | 12 | let template = null; 13 | let modal = this; 14 | 15 | const templateUrl = this.getAttribute("templateUrl"); 16 | const templateSelector = this.getAttribute("templateSelector"); 17 | const workerBaseUrl = this.getAttribute("workerBaseUrl"); 18 | 19 | if (templateUrl !== null) { 20 | fetch(templateUrl) 21 | .then(function(response) { 22 | // When the page is loaded convert it to text 23 | return response.text() 24 | }) 25 | .then(function(html) { 26 | // Initialize the DOM parser 27 | let parser = new DOMParser(); 28 | 29 | // Parse the text 30 | template = parser.parseFromString(html, "text/html"); 31 | let whisperTempl = template.querySelector('#whisper-client-template').cloneNode(true); 32 | modal.innerHTML = whisperTempl.innerHTML; 33 | loadWhisperClient(modal, workerBaseUrl); 34 | }) 35 | .catch(function(err) { 36 | console.log('Template error: ', err); 37 | }); 38 | } else { 39 | modal.innerHTML = document.querySelector(templateSelector).innerHTML; 40 | document.querySelector(templateSelector).remove(); 41 | loadWhisperClient(modal, workerBaseUrl); 42 | } 43 | } 44 | } 45 | 46 | customElements.define('client-whisper-service', WhisperService); 47 | 48 | function loadWhisperClient(modal, workerBaseUrl) { 49 | 50 | console.log("loading whisper client"); 51 | 52 | const fileUploadBtn = document.getElementById("file-input"); 53 | const formSubmitBtn = document.getElementById("form-submit-btn"); 54 | const modelNameSelectionInput = document.getElementById("model-name-input"); 55 | const videoPlayer = document.getElementById("hyperplayer"); 56 | 57 | 58 | if (workerBaseUrl === undefined || workerBaseUrl === null) { 59 | workerBaseUrl = "./"; 60 | } 61 | 62 | const whisperWorkerPath = workerBaseUrl + "js/whisper.worker.js"; 63 | 64 | let webWorker = createWorker(); 65 | 66 | formSubmitBtn.addEventListener("click", async (event2) => { 67 | await handleFormSubmission(); 68 | }); 69 | 70 | function createWorker() { 71 | const worker = new Worker(whisperWorkerPath, { type: "module" }); 72 | 73 | let results = []; 74 | worker.onmessage = (event) => { 75 | handleInferenceDone(event.data); 76 | }; 77 | 78 | return worker; 79 | } 80 | 81 | function handleInferenceDone(results) { 82 | 83 | videoPlayer.currentTime = 0; 84 | 85 | let hypertranscript = ""; 86 | let sentences = 0; 87 | let lastWord = ""; 88 | 89 | results.output.chunks.forEach((word) => { 90 | 91 | // ignore text with square brackets - usually contains things like [BLANK _AUDIO] 92 | if (word.text.indexOf("[") < 0 && word.text.indexOf("]") < 0) { 93 | let start = Math.floor(word.timestamp[0]*1000); 94 | let duration = Math.floor((word.timestamp[1]*1000)-1) - start; 95 | let wordCapitalised = false; 96 | 97 | if (Array.from(word.text)[0].toUpperCase() === Array.from(word.text)[0]){ 98 | wordCapitalised = true; 99 | } 100 | 101 | if (wordCapitalised === true && lastWord.endsWith(".") ){ 102 | sentences += 1; 103 | } 104 | 105 | lastWord = word.text; 106 | 107 | // new para every 5 sentences 108 | if (sentences % 5 === 0 && sentences !== 0) { 109 | hypertranscript += "\n

    \n

    \n"; 110 | sentences = 0; 111 | } 112 | 113 | hypertranscript += `${word.text} \n`; 114 | } 115 | }); 116 | 117 | const resultsContainer = document.getElementById("hypertranscript"); 118 | resultsContainer.innerHTML = "

    \n
    \n

    \n" + hypertranscript + "

    \n
    \n
    \n"; 119 | 120 | const initEvent = new CustomEvent('hyperaudioInit'); 121 | document.dispatchEvent(initEvent); 122 | const capEvent = new CustomEvent('hyperaudioGenerateCaptionsFromTranscript'); 123 | document.dispatchEvent(capEvent); 124 | } 125 | 126 | async function handleFormSubmission() { 127 | 128 | const model_name = modelNameSelectionInput.value; 129 | const file = fileUploadBtn.files[0]; 130 | const audio = await readAudioFrom(file); 131 | 132 | webWorker.postMessage({ 133 | type: "INFERENCE_REQUEST", 134 | audio, 135 | model_name 136 | }); 137 | 138 | videoPlayer.src = URL.createObjectURL(file); 139 | 140 | if (document.querySelector('#transcribe-dialog') !== null){ 141 | document.querySelector('#transcribe-dialog').close(); 142 | } 143 | 144 | const loadingMessageContainer = document.getElementById("hypertranscript"); 145 | 146 | console.log("show spinner"); 147 | console.log(loadingMessageContainer); 148 | 149 | loadingMessageContainer.innerHTML = '
    Transcribing....

    transcribing
    '; 150 | } 151 | 152 | async function readAudioFrom(file) { 153 | const sampling_rate = 16e3; 154 | const audioCTX = new AudioContext({ sampleRate: sampling_rate }); 155 | const response = await file.arrayBuffer(); 156 | const decoded = await audioCTX.decodeAudioData(response); 157 | const audio = decoded.getChannelData(0); 158 | return audio; 159 | } 160 | } -------------------------------------------------------------------------------- /js/hyperaudio-lite-extension.js: -------------------------------------------------------------------------------- 1 | /*! (C) The Hyperaudio Project. MIT @license: en.wikipedia.org/wiki/MIT_License. */ 2 | 3 | 'use strict'; 4 | // Example wrapper for hyperaudio-lite with search and playbackRate included 5 | 6 | let searchForm = document.getElementById('searchForm'); 7 | 8 | if (searchForm) { 9 | searchForm.addEventListener('submit', function(event){ 10 | searchPhrase(document.getElementById('search').value); 11 | event.preventDefault(); 12 | }, false); 13 | } 14 | 15 | document.querySelector('#search-box').addEventListener("keyup", (event) => { 16 | if (event.isComposing || event.keyCode === 229) { 17 | return; 18 | } 19 | 20 | searchPhrase(document.querySelector('#search-box').value); 21 | }); 22 | 23 | 24 | let searchPhrase = function (phrase) { 25 | 26 | let htmlWords = document.querySelectorAll('[data-m]'); 27 | let htmlWordsLen = htmlWords.length; 28 | 29 | let phraseWords = phrase.split(" "); 30 | let phraseWordsLen = phraseWords.length; 31 | let matchedTimes = []; 32 | 33 | // clear matched times 34 | let searchMatched = document.querySelectorAll('.search-match'); 35 | 36 | searchMatched.forEach((match) => { 37 | match.classList.remove('search-match'); 38 | }); 39 | 40 | for (let i = 0; i < htmlWordsLen; i++) { 41 | let numWordsMatched = 0; 42 | let potentiallyMatched = []; 43 | 44 | for (let j = 0; j < phraseWordsLen; j++) { 45 | let wordIndex = i + numWordsMatched; 46 | 47 | if (wordIndex >= htmlWordsLen) { 48 | break; 49 | } 50 | 51 | // regex removes punctuation - NB for htmlWords case we also remove the space 52 | 53 | if (phraseWords[j].toLowerCase() == htmlWords[wordIndex].innerHTML.toLowerCase().replace(/[\.,-\/#!$%\^&\*;:{}=\-_`~()\? ]/g,"")) { 54 | potentiallyMatched.push(htmlWords[wordIndex].getAttribute('data-m')); 55 | numWordsMatched++; 56 | } else { 57 | break; 58 | } 59 | 60 | // if the num of words matched equal the search phrase we have a winner! 61 | if (numWordsMatched >= phraseWordsLen) { 62 | matchedTimes = matchedTimes.concat(potentiallyMatched); 63 | } 64 | } 65 | } 66 | 67 | // display 68 | matchedTimes.forEach(matchedTime => { 69 | document.querySelectorAll("[data-m='"+matchedTime+"']")[0].classList.add("search-match"); 70 | }); 71 | } 72 | 73 | const playbackRateCtrl = document.getElementById('pbr'); 74 | const currentPlaybackRate = document.getElementById('currentPbr'); 75 | 76 | if (playbackRateCtrl !== null) { 77 | playbackRateCtrl.addEventListener('input', function(){ 78 | currentPlaybackRate.value = playbackRateCtrl.value; 79 | hyperplayer.playbackRate = playbackRateCtrl.value; 80 | },false); 81 | } 82 | 83 | if (currentPlaybackRate !== null) { 84 | currentPlaybackRate.addEventListener('change', function(){ 85 | playbackRateCtrl.value = currentPlaybackRate.value; 86 | hyperplayer.playbackRate = playbackRateCtrl.value; 87 | },false); 88 | } -------------------------------------------------------------------------------- /js/hyperaudio-lite.js: -------------------------------------------------------------------------------- 1 | /*! (C) The Hyperaudio Project. MIT @license: en.wikipedia.org/wiki/MIT_License. */ 2 | /*! Version 2.3.2 */ 3 | 4 | 'use strict'; 5 | 6 | // Base player class to handle common player functionality 7 | class BasePlayer { 8 | constructor(instance) { 9 | this.player = this.initPlayer(instance); // Initialize the player 10 | this.paused = true; // Set initial paused state 11 | if (this.player) { 12 | this.attachEventListeners(instance); // Attach event listeners for play and pause 13 | } 14 | } 15 | 16 | // Method to initialize the player - to be implemented by subclasses 17 | initPlayer(instance) { 18 | throw new Error('initPlayer method should be implemented by subclasses'); 19 | } 20 | 21 | // Method to attach common event listeners 22 | attachEventListeners(instance) { 23 | this.player.addEventListener('pause', instance.pausePlayHead.bind(instance), false); 24 | this.player.addEventListener('play', instance.preparePlayHead.bind(instance), false); 25 | } 26 | 27 | // Method to get the current time of the player 28 | getTime() { 29 | return Promise.resolve(this.player.currentTime); 30 | } 31 | 32 | // Method to set the current time of the player 33 | setTime(seconds) { 34 | this.player.currentTime = seconds; 35 | } 36 | 37 | // Method to play the media 38 | play() { 39 | this.player.play(); 40 | this.paused = false; 41 | } 42 | 43 | // Method to pause the media 44 | pause() { 45 | this.player.pause(); 46 | this.paused = true; 47 | } 48 | } 49 | 50 | // Class for native HTML5 player 51 | class NativePlayer extends BasePlayer { 52 | // Initialize the native HTML5 player 53 | initPlayer(instance) { 54 | return instance.player; 55 | } 56 | } 57 | 58 | // Class for SoundCloud player 59 | class SoundCloudPlayer extends BasePlayer { 60 | // Initialize the SoundCloud player 61 | initPlayer(instance) { 62 | return SC.Widget(instance.player.id); 63 | } 64 | 65 | // Attach event listeners specific to SoundCloud player 66 | attachEventListeners(instance) { 67 | this.player.bind(SC.Widget.Events.PAUSE, instance.pausePlayHead.bind(instance)); 68 | this.player.bind(SC.Widget.Events.PLAY, instance.preparePlayHead.bind(instance)); 69 | } 70 | 71 | // Get the current time of the SoundCloud player 72 | getTime() { 73 | return new Promise(resolve => { 74 | this.player.getPosition(ms => resolve(ms / 1000)); 75 | }); 76 | } 77 | 78 | // Set the current time of the SoundCloud player 79 | setTime(seconds) { 80 | this.player.seekTo(seconds * 1000); 81 | } 82 | } 83 | 84 | // Class for VideoJS player 85 | class VideoJSPlayer extends BasePlayer { 86 | // Initialize the VideoJS player 87 | initPlayer(instance) { 88 | return videojs.getPlayer(instance.player.id); 89 | } 90 | 91 | // Get the current time of the VideoJS player 92 | getTime() { 93 | return Promise.resolve(this.player.currentTime()); 94 | } 95 | 96 | // Set the current time of the VideoJS player 97 | setTime(seconds) { 98 | this.player.currentTime(seconds); 99 | } 100 | } 101 | 102 | // Class for Vimeo player 103 | class VimeoPlayer extends BasePlayer { 104 | // Initialize the Vimeo player 105 | initPlayer(instance) { 106 | const iframe = document.querySelector('iframe'); 107 | return new Vimeo.Player(iframe); 108 | } 109 | 110 | // Attach event listeners specific to Vimeo player 111 | attachEventListeners(instance) { 112 | this.player.ready().then(instance.checkPlayHead.bind(instance)); 113 | this.player.on('play', instance.preparePlayHead.bind(instance)); 114 | this.player.on('pause', instance.pausePlayHead.bind(instance)); 115 | } 116 | 117 | // Get the current time of the Vimeo player 118 | getTime() { 119 | return this.player.getCurrentTime(); 120 | } 121 | 122 | // Set the current time of the Vimeo player 123 | setTime(seconds) { 124 | this.player.setCurrentTime(seconds); 125 | } 126 | } 127 | 128 | // Class for YouTube player 129 | class YouTubePlayer extends BasePlayer { 130 | // Initialize the YouTube player by loading YouTube IFrame API 131 | initPlayer(instance) { 132 | // Defer attaching event listeners until the player is ready 133 | this.isReady = false; 134 | 135 | // Load the YouTube IFrame API script 136 | if (!document.getElementById('iframe-demo')) { 137 | const tag = document.createElement('script'); 138 | tag.id = 'iframe-demo'; 139 | tag.src = 'https://www.youtube.com/iframe_api'; 140 | const firstScriptTag = document.getElementsByTagName('script')[0]; 141 | firstScriptTag.parentNode.insertBefore(tag, firstScriptTag); 142 | } 143 | 144 | // Set the global callback for the YouTube IFrame API 145 | window.onYouTubeIframeAPIReady = this.onYouTubeIframeAPIReady.bind(this, instance); 146 | } 147 | 148 | // Callback when YouTube IFrame API is ready 149 | onYouTubeIframeAPIReady(instance) { 150 | this.player = new YT.Player(instance.player.id, { 151 | events: { 152 | onStateChange: this.onPlayerStateChange.bind(this, instance), 153 | onReady: this.onPlayerReady.bind(this) 154 | } 155 | }); 156 | } 157 | 158 | // Event handler when the YouTube player is ready 159 | onPlayerReady() { 160 | this.isReady = true; 161 | } 162 | 163 | // Handle YouTube player state changes (play, pause) 164 | onPlayerStateChange(instance, event) { 165 | if (event.data === YT.PlayerState.PLAYING) { // Playing 166 | instance.preparePlayHead(); 167 | this.paused = false; 168 | } else if (event.data === YT.PlayerState.PAUSED) { // Paused 169 | instance.pausePlayHead(); 170 | this.paused = true; 171 | } 172 | } 173 | 174 | // Get the current time of the YouTube player 175 | getTime() { 176 | if (this.isReady) { 177 | return Promise.resolve(this.player.getCurrentTime()); 178 | } else { 179 | return Promise.resolve(0); // Return 0 if the player is not ready 180 | } 181 | } 182 | 183 | // Set the current time of the YouTube player 184 | setTime(seconds) { 185 | if (this.isReady) { 186 | this.player.seekTo(seconds, true); 187 | } 188 | } 189 | 190 | // Play the YouTube video 191 | play() { 192 | if (this.isReady) { 193 | this.player.playVideo(); 194 | } 195 | } 196 | 197 | // Pause the YouTube video 198 | pause() { 199 | if (this.isReady) { 200 | this.player.pauseVideo(); 201 | } 202 | } 203 | } 204 | 205 | // Class for Spotify player 206 | class SpotifyPlayer extends BasePlayer { 207 | // Initialize the Spotify player by setting up the Spotify IFrame API 208 | initPlayer(instance) { 209 | window.onSpotifyIframeApiReady = IFrameAPI => { 210 | const element = document.getElementById(instance.player.id); 211 | const srcValue = element.getAttribute('src'); 212 | const episodeID = this.extractEpisodeID(srcValue); 213 | 214 | const options = { uri: `spotify:episode:${episodeID}` }; 215 | const callback = player => { 216 | this.player = player; 217 | player.addListener('playback_update', e => { 218 | if (e.data.isPaused !== true) { 219 | this.currentTime = e.data.position / 1000; 220 | instance.preparePlayHead(); 221 | this.paused = false; 222 | } else { 223 | instance.pausePlayHead(); 224 | this.paused = true; 225 | } 226 | }); 227 | 228 | player.addListener('ready', () => { 229 | player.togglePlay(); // Priming the playhead 230 | instance.checkPlayHead(); 231 | }); 232 | }; 233 | 234 | IFrameAPI.createController(element, options, callback); 235 | }; 236 | } 237 | 238 | // Extract episode ID from the Spotify URL 239 | extractEpisodeID(url) { 240 | const match = url.match(/episode\/(.+)$/); 241 | return match ? match[1] : null; 242 | } 243 | 244 | // Get the current time of the Spotify player 245 | getTime() { 246 | return Promise.resolve(this.currentTime); 247 | } 248 | 249 | // Set the current time of the Spotify player 250 | setTime(seconds) { 251 | this.player.seek(seconds); 252 | } 253 | 254 | // Play the Spotify track 255 | play() { 256 | this.player.play(); 257 | this.paused = false; 258 | } 259 | 260 | // Pause the Spotify track 261 | pause() { 262 | this.player.togglePlay(); 263 | this.paused = true; 264 | } 265 | } 266 | 267 | // Mapping player types to their respective classes 268 | const hyperaudioPlayerOptions = { 269 | "native": NativePlayer, 270 | "soundcloud": SoundCloudPlayer, 271 | "youtube": YouTubePlayer, 272 | "videojs": VideoJSPlayer, 273 | "vimeo": VimeoPlayer, 274 | "spotify": SpotifyPlayer 275 | }; 276 | 277 | // Factory function to create player instances 278 | function hyperaudioPlayer(playerType, instance) { 279 | if (playerType) { 280 | return new hyperaudioPlayerOptions[playerType](instance); 281 | } else { 282 | console.warn("HYPERAUDIO LITE WARNING: data-player-type attribute should be set on player if not native, e.g., SoundCloud, YouTube, Vimeo, VideoJS"); 283 | } 284 | } 285 | 286 | // Main class for HyperaudioLite functionality 287 | class HyperaudioLite { 288 | constructor(transcriptId, mediaElementId, minimizedMode, autoscroll, doubleClick, webMonetization, playOnClick) { 289 | this.transcript = document.getElementById(transcriptId); 290 | this.init(mediaElementId, minimizedMode, autoscroll, doubleClick, webMonetization, playOnClick); 291 | 292 | // Ensure correct binding for class methods 293 | this.preparePlayHead = this.preparePlayHead.bind(this); 294 | this.pausePlayHead = this.pausePlayHead.bind(this); 295 | this.setPlayHead = this.setPlayHead.bind(this); 296 | this.checkPlayHead = this.checkPlayHead.bind(this); 297 | this.clearTimer = this.clearTimer.bind(this); 298 | } 299 | 300 | // Initialize the HyperaudioLite instance 301 | init(mediaElementId, minimizedMode, autoscroll, doubleClick, webMonetization, playOnClick) { 302 | this.setupTranscriptHash(); 303 | this.setupPopover(); 304 | this.setupPlayer(mediaElementId); 305 | this.setupTranscriptWords(); 306 | this.setupEventListeners(doubleClick, playOnClick); 307 | this.setupInitialPlayHead(); 308 | this.setupAutoScroll(autoscroll); 309 | this.minimizedMode = minimizedMode; 310 | this.autoscroll = autoscroll; 311 | this.webMonetization = webMonetization; 312 | this.scrollerContainer = this.transcript; 313 | } 314 | 315 | // Setup hash for transcript selection 316 | setupTranscriptHash() { 317 | const windowHash = window.location.hash; 318 | const hashVar = windowHash.substring(1, windowHash.indexOf('=')); 319 | 320 | if (hashVar === this.transcript.id) { 321 | this.hashArray = windowHash.substring(this.transcript.id.length + 2).split(','); 322 | } else { 323 | this.hashArray = []; 324 | } 325 | } 326 | 327 | // Setup the popover for text selection 328 | setupPopover() { 329 | if (typeof popover !== 'undefined') { 330 | this.transcript.addEventListener('mouseup', () => { 331 | const selection = window.getSelection(); 332 | const popover = document.getElementById('popover'); 333 | let selectionText; 334 | 335 | if (selection.toString().length > 0) { 336 | selectionText = selection.toString().replaceAll("'", "`"); 337 | const range = selection.getRangeAt(0); 338 | const rect = range.getBoundingClientRect(); 339 | 340 | popover.style.left = `${rect.left + window.scrollX}px`; 341 | popover.style.top = `${rect.bottom + window.scrollY}px`; 342 | popover.style.display = 'block'; 343 | 344 | const mediaFragment = this.getSelectionMediaFragment(); 345 | 346 | if (mediaFragment) { 347 | document.location.hash = mediaFragment; 348 | } 349 | } else { 350 | popover.style.display = 'none'; 351 | } 352 | 353 | const popoverBtn = document.getElementById('popover-btn'); 354 | popoverBtn.addEventListener('click', (e) => { 355 | popover.style.display = 'none'; 356 | let cbText = `${selectionText} ${document.location}`; 357 | navigator.clipboard.writeText(cbText); 358 | 359 | const dialog = document.getElementById("clipboard-dialog"); 360 | document.getElementById("clipboard-text").innerHTML = cbText; 361 | dialog.showModal(); 362 | 363 | const confirmButton = document.getElementById("clipboard-confirm"); 364 | confirmButton.addEventListener("click", () => dialog.close()); 365 | 366 | e.preventDefault(); 367 | return false; 368 | }); 369 | }); 370 | } 371 | } 372 | 373 | // Setup the media player 374 | setupPlayer(mediaElementId) { 375 | this.player = document.getElementById(mediaElementId); 376 | const mediaSrc = this.transcript.querySelector('[data-media-src]'); 377 | if (mediaSrc) { 378 | this.player.src = mediaSrc.getAttribute('data-media-src'); 379 | } 380 | 381 | if (this.player.tagName === 'VIDEO' || this.player.tagName === 'AUDIO') { 382 | this.playerType = 'native'; 383 | } else { 384 | this.playerType = this.player.getAttribute('data-player-type'); 385 | } 386 | 387 | this.myPlayer = hyperaudioPlayer(this.playerType, this); 388 | } 389 | 390 | // Setup the transcript words 391 | setupTranscriptWords() { 392 | const words = this.transcript.querySelectorAll('[data-m]'); 393 | this.wordArr = this.createWordArray(words); 394 | 395 | // check for elements with data-m attributes that are not directly below
    396 | // these will contain

    or similar that we can scroll to 397 | 398 | for (const word of words) { 399 | let parentTagName = word.parentElement.tagName; 400 | if (parentTagName !== "SECTION") { 401 | this.parentTag = parentTagName; 402 | break; 403 | } 404 | } 405 | 406 | this.parentElements = this.transcript.getElementsByTagName(this.parentTag); 407 | } 408 | 409 | setupAutoScroll(autoscroll) { 410 | if (autoscroll) { 411 | if (window.Velocity) { 412 | this.scroller = window.Velocity; 413 | } else if (window.jQuery && window.jQuery.Velocity) { 414 | this.scroller = window.jQuery.Velocity; 415 | } 416 | } 417 | } 418 | 419 | // Setup event listeners for interactions 420 | setupEventListeners(doubleClick, playOnClick) { 421 | this.minimizedMode = false; 422 | this.autoscroll = false; 423 | this.doubleClick = doubleClick; 424 | this.webMonetization = false; 425 | this.playOnClick = playOnClick; 426 | this.highlightedText = false; 427 | this.start = null; 428 | 429 | const playHeadEvent = doubleClick ? 'dblclick' : 'click'; 430 | this.transcript.addEventListener(playHeadEvent, this.setPlayHead.bind(this), false); 431 | this.transcript.addEventListener(playHeadEvent, this.checkPlayHead.bind(this), false); 432 | } 433 | 434 | // Setup initial playhead position based on URL hash 435 | setupInitialPlayHead() { 436 | this.start = this.hashArray[0]; 437 | if (!isNaN(parseFloat(this.start))) { 438 | this.highlightedText = true; 439 | let indices = this.updateTranscriptVisualState(this.start); 440 | if (indices.currentWordIndex > 0 && this.autoscroll) { 441 | this.scrollToParagraph(indices.currentParentElementIndex, indices.currentWordIndex); 442 | } 443 | } 444 | 445 | this.end = this.hashArray[1]; 446 | //TODO convert to binary search for below for quicker startup 447 | if (this.start && this.end) { 448 | const words = this.transcript.querySelectorAll('[data-m]'); 449 | for (let i = 1; i < words.length; i++) { 450 | let startTime = parseInt(words[i].getAttribute('data-m')) / 1000; 451 | let wordStart = (Math.round(startTime * 100) / 100).toFixed(2); 452 | if (wordStart >= parseFloat(this.start) && parseFloat(this.end) > wordStart) { 453 | words[i].classList.add('share-match'); 454 | } 455 | } 456 | } 457 | } 458 | 459 | // Create an array of words with metadata from the transcript 460 | createWordArray(words) { 461 | return Array.from(words).map(word => { 462 | const m = parseInt(word.getAttribute('data-m')); 463 | let p = word.parentNode; 464 | while (p !== document) { 465 | if (['p', 'figure', 'ul'].includes(p.tagName.toLowerCase())) { 466 | break; 467 | } 468 | p = p.parentNode; 469 | } 470 | word.classList.add('unread'); 471 | return { n: word, m, p }; 472 | }); 473 | } 474 | 475 | getSelectionRange = () => { 476 | const selection = window.getSelection(); 477 | if (selection.rangeCount === 0) return null; 478 | 479 | const range = selection.getRangeAt(0); 480 | 481 | // Helper function to get the closest span 482 | function getClosestSpan(node) { 483 | while (node && node.nodeType !== Node.ELEMENT_NODE) { 484 | node = node.parentNode; 485 | } 486 | return node.closest('[data-m]'); 487 | } 488 | 489 | // Get all relevant spans 490 | const allSpans = Array.from(this.transcript.querySelectorAll('[data-m]')); 491 | 492 | // Find the first and last span that contain selected text 493 | let startSpan = null; 494 | let endSpan = null; 495 | let selectedText = range.toString(); 496 | let trimmedSelectedText = selectedText.trim(); 497 | 498 | for (let span of allSpans) { 499 | if (range.intersectsNode(span) && span.textContent.trim() !== '') { 500 | if (!startSpan) startSpan = span; 501 | endSpan = span; 502 | } 503 | } 504 | 505 | if (!startSpan || !endSpan) return null; 506 | 507 | // Adjust start span if selection starts with a space 508 | let startIndex = allSpans.indexOf(startSpan); 509 | while (selectedText.startsWith(' ') && startIndex < allSpans.length - 1) { 510 | startIndex++; 511 | startSpan = allSpans[startIndex]; 512 | selectedText = selectedText.slice(1); 513 | } 514 | 515 | // Calculate start time 516 | let startTime = parseInt(startSpan.dataset.m) / 1000; 517 | 518 | // Calculate end time 519 | 520 | let duration = 0; 521 | if (endSpan.dataset.d) { 522 | duration = parseInt(endSpan.dataset.d); 523 | } else { 524 | // when no duration exists default to 1 second 525 | duration = 1000; 526 | } 527 | 528 | let endTime = (parseInt(endSpan.dataset.m) + duration) / 1000; 529 | 530 | // Format to seconds at 2 decimal place precision 531 | let startTimeFormatted = (Math.round(startTime * 100) / 100).toFixed(2); 532 | let endTimeFormatted = (Math.round(endTime * 100) / 100).toFixed(2); 533 | 534 | // Only return a range if there's actually selected text (excluding only spaces) 535 | return trimmedSelectedText ? `${startTimeFormatted},${endTimeFormatted}` : null; 536 | } 537 | 538 | getSelectionMediaFragment = () => { 539 | let range = this.getSelectionRange(); 540 | if (range === null) { 541 | return null; 542 | } 543 | console.log(range); 544 | return (this.transcript.id + '=' +range); 545 | } 546 | 547 | // Set the playhead position in the media player based on the transcript 548 | setPlayHead(e) { 549 | const target = e.target || e.srcElement; 550 | this.highlightedText = false; 551 | this.clearActiveClasses(); 552 | 553 | if (this.myPlayer.paused && target.dataset.m) { 554 | target.classList.add('active'); 555 | target.parentNode.classList.add('active'); 556 | } 557 | 558 | const timeSecs = parseInt(target.dataset.m) / 1000; 559 | this.updateTranscriptVisualState(timeSecs); 560 | 561 | if (!isNaN(timeSecs)) { 562 | this.end = null; 563 | this.myPlayer.setTime(timeSecs); 564 | if (this.playOnClick) { 565 | this.myPlayer.play(); 566 | } 567 | } 568 | } 569 | 570 | // Clear the active classes from the transcript 571 | clearActiveClasses() { 572 | const activeElements = Array.from(this.transcript.getElementsByClassName('active')); 573 | activeElements.forEach(e => e.classList.remove('active')); 574 | } 575 | 576 | // Prepare the playhead for playback 577 | preparePlayHead() { 578 | this.myPlayer.paused = false; 579 | this.checkPlayHead(); 580 | } 581 | 582 | // Pause the playhead 583 | pausePlayHead() { 584 | this.clearTimer(); 585 | this.myPlayer.paused = true; 586 | } 587 | 588 | // Check the playhead position and update the transcript 589 | checkPlayHead() { 590 | this.clearTimer(); 591 | 592 | (async () => { 593 | this.currentTime = await this.myPlayer.getTime(); 594 | if (this.highlightedText) { 595 | this.currentTime = this.start; 596 | this.myPlayer.setTime(this.currentTime); 597 | this.highlightedText = false; 598 | } 599 | this.checkStatus(); 600 | })(); 601 | } 602 | 603 | // Clear the timer for the playhead 604 | clearTimer() { 605 | if (this.timer) { 606 | clearTimeout(this.timer); 607 | this.timer = null; 608 | } 609 | } 610 | 611 | // Scroll to the paragraph containing the current word 612 | scrollToParagraph(currentParentElementIndex, index) { 613 | 614 | const scrollNode = this.wordArr[index - 1].n.closest('p') || this.wordArr[index - 1].n; 615 | 616 | if (currentParentElementIndex !== this.parentElementIndex) { 617 | if (this.autoscroll && typeof this.scroller !== 'undefined') { 618 | if (scrollNode) { 619 | this.scroller(scrollNode, 'scroll', { 620 | container: this.scrollerContainer, 621 | duration: this.scrollerDuration, 622 | delay: this.scrollerDelay, 623 | offset: this.scrollerOffset, 624 | }); 625 | } else { 626 | this.wordArr = this.createWordArray(this.transcript.querySelectorAll('[data-m]')); 627 | this.parentElements = this.transcript.getElementsByTagName(this.parentTag); 628 | } 629 | } 630 | this.parentElementIndex = currentParentElementIndex; 631 | } 632 | } 633 | 634 | // Check the status of the playhead and update the transcript 635 | checkStatus() { 636 | if (!this.myPlayer.paused) { 637 | if (this.end && parseInt(this.end) < parseInt(this.currentTime)) { 638 | this.myPlayer.pause(); 639 | this.end = null; 640 | } else { 641 | const indices = this.updateTranscriptVisualState(this.currentTime); 642 | const index = indices.currentWordIndex; 643 | 644 | if (index > 0 && this.autoscroll) { 645 | this.scrollToParagraph(indices.currentParentElementIndex, index); 646 | } 647 | 648 | if (this.minimizedMode) { 649 | const elements = this.transcript.querySelectorAll('[data-m]'); 650 | let currentWord = ''; 651 | let lastWordIndex = this.wordIndex; 652 | 653 | for (let i = 0; i < elements.length; i++) { 654 | if (elements[i].classList.contains('active')) { 655 | currentWord = elements[i].innerHTML; 656 | this.wordIndex = i; 657 | } 658 | } 659 | 660 | if (this.wordIndex !== lastWordIndex) { 661 | document.title = currentWord; 662 | } 663 | } 664 | 665 | if (this.webMonetization === true) { 666 | //check for payment pointer 667 | let activeElements = this.transcript.getElementsByClassName('active'); 668 | let paymentPointer = this.checkPaymentPointer(activeElements[activeElements.length - 1]); 669 | 670 | if (paymentPointer !== null) { 671 | let metaElements = document.getElementsByTagName('meta'); 672 | let wmMeta = document.querySelector("meta[name='monetization']"); 673 | if (wmMeta === null) { 674 | wmMeta = document.createElement('meta'); 675 | wmMeta.name = 'monetization'; 676 | wmMeta.content = paymentPointer; 677 | document.getElementsByTagName('head')[0].appendChild(wmMeta); 678 | } else { 679 | wmMeta.name = 'monetization'; 680 | wmMeta.content = paymentPointer; 681 | } 682 | } 683 | } 684 | 685 | let interval = 0; 686 | if (this.wordArr[index]) { 687 | interval = this.wordArr[index].n.getAttribute('data-m') - this.currentTime * 1000; 688 | } 689 | 690 | this.timer = setTimeout(() => this.checkPlayHead(), interval + 1); 691 | } 692 | } else { 693 | this.clearTimer(); 694 | } 695 | } 696 | 697 | checkPaymentPointer = element => { 698 | let paymentPointer = null; 699 | 700 | if (typeof(element) != "undefined") { 701 | paymentPointer = element.getAttribute('data-wm'); 702 | } 703 | 704 | if (paymentPointer !== null) { 705 | return paymentPointer; 706 | } else { 707 | let parent = null; 708 | 709 | if (typeof element !== 'undefined') { 710 | parent = element.parentElement; 711 | } 712 | 713 | if (parent === null) { 714 | return null; 715 | } else { 716 | return this.checkPaymentPointer(parent); 717 | } 718 | } 719 | } 720 | 721 | // Update the visual state of the transcript based on the current time 722 | updateTranscriptVisualState(currentTime) { 723 | let index = 0; 724 | let words = this.wordArr.length - 1; 725 | 726 | while (index <= words) { 727 | const guessIndex = index + ((words - index) >> 1); 728 | const difference = this.wordArr[guessIndex].m / 1000 - currentTime; 729 | 730 | if (difference < 0) { 731 | index = guessIndex + 1; 732 | } else if (difference > 0) { 733 | words = guessIndex - 1; 734 | } else { 735 | index = guessIndex; 736 | break; 737 | } 738 | } 739 | 740 | this.wordArr.forEach((word, i) => { 741 | const classList = word.n.classList; 742 | const parentClassList = word.n.parentNode.classList; 743 | 744 | if (i < index) { 745 | classList.add('read'); 746 | classList.remove('unread', 'active'); 747 | parentClassList.remove('active'); 748 | } else { 749 | classList.add('unread'); 750 | classList.remove('read'); 751 | } 752 | }); 753 | 754 | this.parentElements = this.transcript.getElementsByTagName(this.parentTag); 755 | Array.from(this.parentElements).forEach(el => el.classList.remove('active')); 756 | 757 | if (index > 0) { 758 | if (!this.myPlayer.paused) { 759 | this.wordArr[index - 1].n.classList.add('active'); 760 | } 761 | this.wordArr[index - 1].n.parentNode.classList.add('active'); 762 | } 763 | 764 | const currentParentElementIndex = Array.from(this.parentElements).findIndex(el => el.classList.contains('active')); 765 | 766 | return { 767 | currentWordIndex: index, 768 | currentParentElementIndex 769 | }; 770 | } 771 | } 772 | 773 | // Export for testing or module usage 774 | if (typeof module !== 'undefined' && module.exports) { 775 | module.exports = { HyperaudioLite }; 776 | } -------------------------------------------------------------------------------- /js/hyperaudio-push-notification.js: -------------------------------------------------------------------------------- 1 | /*! (C) The Hyperaudio Project. MIT @license: en.wikipedia.org/wiki/MIT_License. */ 2 | /*! Last modified for Version 0.3.1 */ 3 | 4 | Notification.requestPermission().then(perm => { 5 | console.log('permission: ', perm) 6 | }) 7 | 8 | const notifyTranscriptionReady = () => { 9 | let notification = new Notification("Your Hyperaudio transcript is ready!", { 10 | body: "Click here to see your transcript." 11 | }) 12 | 13 | notification.onclick = () => { 14 | window.parent.parent.focus(); 15 | } 16 | 17 | } 18 | 19 | window.document.addEventListener('hyperaudioInit', notifyTranscriptionReady, false); -------------------------------------------------------------------------------- /js/whisper.worker.js: -------------------------------------------------------------------------------- 1 | import { pipeline } from "https://cdn.jsdelivr.net/npm/@xenova/transformers@2.11.0"; 2 | 3 | self.addEventListener("message", async (event) => { 4 | const { type, audio, model_name } = event.data; 5 | 6 | if (type === "INFERENCE_REQUEST") { 7 | 8 | const automaticSpeechRecognition = await pipeline( 9 | "automatic-speech-recognition", 10 | model_name, 11 | { revision: "output_attentions" } 12 | ); 13 | 14 | let output = await automaticSpeechRecognition(audio, { 15 | return_timestamps: "word", 16 | chunk_length_s: 30, 17 | stride_length_s: 5, 18 | }); 19 | 20 | console.log(output); 21 | self.postMessage({ output: output }); 22 | } 23 | }); -------------------------------------------------------------------------------- /local.html: -------------------------------------------------------------------------------- 1 | 2 | 3 |

    4 | 5 | 6 |
    7 | 8 | 9 | 49 | 50 | 51 | -------------------------------------------------------------------------------- /manifest.json: -------------------------------------------------------------------------------- 1 | { 2 | "name":"Hyperaudio Lite Editor", 3 | "short_name":"HLE", 4 | "start_url":"/hyperaudio-lite-editor/index.html", 5 | "scope":"/hyperaudio-lite-editor/", 6 | "display":"standalone", 7 | "background_color":"#6100DF", 8 | "theme_color":"#6100DF", 9 | "description":"A super-lightweight transcript editor", 10 | "icons":[ 11 | { 12 | "src":"images/icon-192x192.png", 13 | "sizes":"192x192", 14 | "type":"image/png" 15 | }, 16 | { 17 | "src":"images/icon-512x512.png", 18 | "sizes":"512x512", 19 | "type":"image/png" 20 | }, 21 | { 22 | "src":"images/maskable-icon-192x192.png", 23 | "sizes":"192x192", 24 | "type":"image/png", 25 | "purpose": "any maskable" 26 | } 27 | ] 28 | } 29 | -------------------------------------------------------------------------------- /package.json: -------------------------------------------------------------------------------- 1 | { 2 | "devDependencies": { 3 | "autoprefixer": "^10.4.14", 4 | "cssnano": "^6.0.1", 5 | "daisyui": "^3.1.9", 6 | "postcss": "^8.4.24", 7 | "tailwindcss": "^3.3.2" 8 | } 9 | } 10 | -------------------------------------------------------------------------------- /postcss.config.js: -------------------------------------------------------------------------------- 1 | module.exports = { 2 | plugins: { 3 | tailwindcss: {}, 4 | autoprefixer: {}, 5 | ...(process.env.NODE_ENV === 'production' ? { cssnano: {} } : {}) 6 | } 7 | } 8 | 9 | 10 | -------------------------------------------------------------------------------- /serviceworker.js: -------------------------------------------------------------------------------- 1 | var staticCacheName = "pwa"; 2 | 3 | self.addEventListener("install", function (e) { 4 | e.waitUntil( 5 | caches.open(staticCacheName).then(function (cache) { 6 | return cache.addAll(["https://hyperaudio.github.io/hyperaudio-lite-editor/"]); 7 | }) 8 | ); 9 | }); 10 | 11 | self.addEventListener("fetch", function (event) { 12 | console.log(event.request.url); 13 | event.respondWith( 14 | caches.match(event.request).then(function (response) { 15 | return response || fetch(event.request); 16 | }) 17 | ); 18 | }); -------------------------------------------------------------------------------- /tailwind.config.js: -------------------------------------------------------------------------------- 1 | /** @type {import('tailwindcss').Config} */ 2 | module.exports = { 3 | content: [ 4 | "*.{html,js}", 5 | "js/*.{html,js}", 6 | ], 7 | theme: { 8 | extend: {}, 9 | }, 10 | plugins: [ 11 | //require("tailwindcss"), 12 | //require("autoprefixer"), 13 | require("daisyui"), 14 | ], 15 | }; 16 | -------------------------------------------------------------------------------- /tailwind.md: -------------------------------------------------------------------------------- 1 | # Tailwind CSS Guide 2 | 3 | This document outlines the steps to install and configure Tailwind CSS for your project. Tailwind CSS is a highly customizable, low-level CSS framework that gives you all of the building blocks you need to build bespoke designs without any annoying opinionated styles you have to fight to override. 4 | 5 | ## Installation 6 | 7 | Tailwind CSS relies on a few dependencies. To install these, run the following command in your project directory: 8 | 9 | ```bash 10 | npm install -D tailwindcss postcss autoprefixer cssnano daisyui@latest 11 | ``` 12 | 13 | This will install Tailwind CSS, PostCSS, Autoprefixer, and CSSNano. These tools are used to process your CSS files. 14 | 15 | ## Development Build 16 | 17 | For development purposes, you can create a specific Tailwind CSS file that includes all styles. This is useful for live-reloading and previewing changes during development. 18 | 19 | Run this command to create the development build: 20 | 21 | ```bash 22 | npx tailwindcss -i ./config/tailwind.css -o ./css/tailwind-dev.css --watch 23 | ``` 24 | 25 | The `-i` option specifies the input file, `-o` specifies the output file, and `--watch` makes the process keep running, automatically rebuilding when you make changes to your CSS. 26 | 27 | ## Production Build 28 | 29 | For a production build, you'll want to minify your CSS to reduce file size. This process removes all the spaces, line breaks, and comments that make CSS readable to humans but are unnecessary for machines. 30 | 31 | To create a minified version of your CSS, run: 32 | 33 | ```bash 34 | npx tailwindcss -o ./css/tailwind-min.css --minify 35 | ``` 36 | 37 | The `--minify` option will output a minified version of your CSS suitable for production use. 38 | 39 | ## Custom Configuration 40 | 41 | Tailwind CSS can be customized to fit your project's needs. You can adjust your settings in the `tailwind.config.js` file, and you can add your own styles to the `config/tailwind.css` file. 42 | 43 | ## Minification Configuration 44 | 45 | If you need to configure the minification process or add more PostCSS plugins, you can modify the `postcss.config.js` file. This file defines how PostCSS should process your CSS. 46 | 47 | Remember to test your changes thoroughly before pushing to production to ensure that your styles are applied correctly. 48 | -------------------------------------------------------------------------------- /test/test.mp3: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperaudio/hyperaudio-lite-editor/f51106e7aed1fe47d1f43e0a897071c51221a5bb/test/test.mp3 --------------------------------------------------------------------------------