├── __init__.py ├── pyproject.toml ├── .github └── workflows │ └── publish.yml ├── README.md ├── IFParlerTTSNode.py └── LICENSE /__init__.py: -------------------------------------------------------------------------------- 1 | import os 2 | import importlib.util 3 | import glob 4 | import shutil 5 | 6 | from .IFParlerTTSNode import IFParlerTTS 7 | 8 | NODE_CLASS_MAPPINGS = { 9 | "IF_ParlerTTS": IFParlerTTS 10 | } 11 | 12 | NODE_DISPLAY_NAME_MAPPINGS = { 13 | 14 | "IF_ParlerTTS": "IF Parler TTS🎤" 15 | } 16 | 17 | WEB_DIRECTORY = "./web" 18 | __all__ = ["NODE_CLASS_MAPPINGS", "NODE_DISPLAY_NAME_MAPPINGS", "WEB_DIRECTORY"] 19 | -------------------------------------------------------------------------------- /pyproject.toml: -------------------------------------------------------------------------------- 1 | [project] 2 | name = "comfyui-if_ai_parlerttsnode" 3 | description = "Parler TTS is a zeroshot voice synthesis with emotion and entonations, you can control the voice style via text prompt" 4 | version = "1.0.1" 5 | license = { file = "MIT License" } 6 | 7 | [project.urls] 8 | Repository = "https://github.com/if-ai/ComfyUI-IF_AI_ParlerTTSNode" 9 | # Used by Comfy Registry https://comfyregistry.org 10 | 11 | [tool.comfy] 12 | PublisherId = "impactframes" 13 | DisplayName = "IF_ParlerTTSNode" 14 | Icon = "https://impactframes.ai/System/Icons/48x48/if.png" 15 | -------------------------------------------------------------------------------- /.github/workflows/publish.yml: -------------------------------------------------------------------------------- 1 | name: Publish to Comfy registry 2 | on: 3 | workflow_dispatch: 4 | push: 5 | branches: 6 | - main 7 | paths: 8 | - "pyproject.toml" 9 | 10 | permissions: 11 | issues: write 12 | 13 | jobs: 14 | publish-node: 15 | name: Publish Custom Node to registry 16 | runs-on: ubuntu-latest 17 | if: ${{ github.repository_owner == 'if-ai' }} 18 | steps: 19 | - name: Check out code 20 | uses: actions/checkout@v4 21 | - name: Publish Custom Node 22 | uses: Comfy-Org/publish-node-action@v1 23 | with: 24 | ## Add your own personal access token to your Github Repository secrets and reference it here. 25 | personal_access_token: ${{ secrets.REGISTRY_ACCESS_TOKEN }} 26 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # IF_ParlerTTSNode: Comfy Node for Parler TTS 2 | 3 | This node provides access to the high-quality Parler TTS with promptable descriptions within ComfyUI. It is part of the IF_AI_tools collection. 4 | 5 | ## Installation 6 | 7 | **Prerequisites:** 8 | 9 | * **Python environment:** You need a Python environment with pip. You can use virtual environments like venv or conda environments. 10 | * **ComfyUI:** Ensure you have ComfyUI installed and set up. 11 | 12 | **Installation Steps:** 13 | 14 | 1. **Activate your Python environment.** 15 | 2. **Install Parler TTS:** 16 | * **Linux/macOS:** 17 | ```bash 18 | pip install git+https://github.com/huggingface/parler-tts.git 19 | ``` 20 | * **Windows (Portable Embedded Python):** 21 | ```bash 22 | H:\ComfyUI_windows_portable\python_embeded\python.exe -m pip install git+https://github.com/huggingface/parler-tts.git 23 | ``` 24 | 3. **Install ffmpy (if necessary):** 25 | * If you encounter issues with ffmpy, follow these instructions: 26 | 1. Download ffmpy from https://pypi.org/project/ffmpy/#files 27 | 2. Extract the downloaded code. 28 | 3. In the `setup.py` file, comment out line 4 (`#from ffmpy import __version__`). 29 | 4. Change the version string on line 8 to the actual version (e.g., `version="0.3.0"`). 30 | 5. Open a terminal in the extracted ffmpy directory. 31 | 6. Run the following command, replacing `` with the path to your Python executable: 32 | ```bash 33 | setup.py 34 | ``` 35 | 4. **Install importlib_resources (Windows Portable Embedded Python only):** 36 | ```bash 37 | H:\ComfyUI_windows_portable\python_embeded\python.exe -m pip install importlib_resources 38 | ``` 39 | 40 | ## Usage 41 | 42 | 1. Once installed, the Parler TTS node should be available within ComfyUI. 43 | 2. You can use it to generate speech audio from text prompts, including descriptive details for controlling the speech style and characteristics. 44 | 45 | ## Additional Notes 46 | 47 | * Refer to the Parler TTS documentation and examples for more information on using the model effectively. 48 | [* T](https://github.com/huggingface/parler-tts) 49 | -------------------------------------------------------------------------------- /IFParlerTTSNode.py: -------------------------------------------------------------------------------- 1 | import os 2 | import torch 3 | import tempfile 4 | import datetime 5 | import torchaudio 6 | import textwrap 7 | import re 8 | import numpy as np 9 | from parler_tts import ParlerTTSForConditionalGeneration 10 | from transformers import AutoTokenizer 11 | import scipy.io.wavfile as wav 12 | import librosa 13 | from nltk.tokenize import sent_tokenize 14 | 15 | class IFParlerTTS: 16 | @classmethod 17 | def INPUT_TYPES(cls): 18 | node = cls() 19 | return { 20 | "required": { 21 | "prompt": ("STRING", {"multiline": True, "default": node.sample_prompt}), 22 | "description": ("STRING", {"multiline": True, "default": node.sample_description}), 23 | "file_name": ("STRING", {"default": node.file_name}), 24 | "cpu": ("BOOLEAN", {"default": False}), 25 | } 26 | } 27 | 28 | RETURN_TYPES = ("AUDIO", "STRING") 29 | RETURN_NAMES = ("audios", "wav_16k_path") 30 | FUNCTION = "generate_audio" 31 | 32 | CATEGORY = "ImpactFrames💥🎞️" 33 | OUTPUT_NODE = True 34 | 35 | def __init__(self): 36 | self.file_name = "IF_ParlerTTS" 37 | self.sample_prompt = "Hey, how are you doing today?" 38 | self.sample_description = "A female speaker with a slightly low-pitched voice delivers her words quite expressively, in a very confined sounding environment with clear audio quality. She speaks very fast." 39 | 40 | def split_and_prepare_text(self, text): 41 | chunks = [] 42 | sentences = sent_tokenize(text) 43 | chunk = "" 44 | for sentence in sentences: 45 | # replace fancy punctuation that was unseen during training 46 | sentence = re.sub('[()]', ",", sentence).strip() 47 | sentence = re.sub(",+", ",", sentence) 48 | sentence = re.sub('"+', "", sentence) 49 | sentence = re.sub("/", "", sentence) 50 | # merge until the result is < 20s 51 | if len(chunk) + len(sentence) < 300: 52 | chunk += " " + sentence 53 | else: 54 | chunks.append(chunk) 55 | chunk = sentence 56 | if chunk: 57 | chunks.append(chunk) 58 | return chunks 59 | 60 | def generate_audio(self, prompt, description, file_name, cpu): 61 | device = "cpu" if cpu else "cuda:0" if torch.cuda.is_available() else "cpu" 62 | model = ParlerTTSForConditionalGeneration.from_pretrained("parler-tts/parler_tts_mini_v0.1").to(device) 63 | tokenizer = AutoTokenizer.from_pretrained("parler-tts/parler_tts_mini_v0.1") 64 | 65 | comfy_dir = os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__file__)))) 66 | timestamp = datetime.datetime.now().strftime("%Y%m%d%H%M%S") 67 | output_name = f"{file_name}_{timestamp}" 68 | output_dir = os.path.join(comfy_dir, "output", output_name) 69 | os.makedirs(output_dir, exist_ok=True) 70 | wav_16k_path = os.path.join(output_dir, f"{output_name}.wav") 71 | tmp_dir = os.path.join(comfy_dir, "temp", output_name) 72 | os.makedirs(tmp_dir, exist_ok=True) 73 | wav_temp_path = os.path.join(tmp_dir, "audio.wav") 74 | 75 | chunks = self.split_and_prepare_text(prompt) 76 | audio_segments = [] 77 | 78 | for chunk in chunks: 79 | input_ids = tokenizer(description, return_tensors="pt").input_ids.to(device) 80 | prompt_input_ids = tokenizer(chunk, return_tensors="pt").input_ids.to(device) 81 | generation = model.generate(input_ids=input_ids, prompt_input_ids=prompt_input_ids) 82 | audio_arr = generation.cpu().numpy().squeeze() 83 | audio_segments.append(torch.from_numpy(audio_arr)) 84 | 85 | # Concatenate the audio segments 86 | audio = torch.cat(audio_segments, dim=-1) 87 | 88 | # Save the audio using scipy.io.wavfile 89 | wav.write(wav_temp_path, model.config.sampling_rate, audio.numpy()) 90 | 91 | # Load the audio using librosa 92 | audio, sr = librosa.load(wav_temp_path, sr=model.config.sampling_rate) 93 | 94 | # Resample the audio to 16kHz using librosa 95 | resampled_audio = librosa.resample(audio, orig_sr=sr, target_sr=16000) 96 | 97 | # Save the resampled audio using scipy.io.wavfile 98 | wav.write(wav_16k_path, 16000, resampled_audio) 99 | 100 | return (audio, wav_16k_path) 101 | 102 | NODE_CLASS_MAPPINGS = {"IF_ParlerTTS": IFParlerTTS} 103 | NODE_DISPLAY_NAME_MAPPINGS = {"IF_ParlerTTS": "IF Parler TTS🎤"} -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | Apache License 2 | Version 2.0, January 2004 3 | http://www.apache.org/licenses/ 4 | 5 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 6 | 7 | 1. Definitions. 8 | 9 | "License" shall mean the terms and conditions for use, reproduction, 10 | and distribution as defined by Sections 1 through 9 of this document. 11 | 12 | "Licensor" shall mean the copyright owner or entity authorized by 13 | the copyright owner that is granting the License. 14 | 15 | "Legal Entity" shall mean the union of the acting entity and all 16 | other entities that control, are controlled by, or are under common 17 | control with that entity. For the purposes of this definition, 18 | "control" means (i) the power, direct or indirect, to cause the 19 | direction or management of such entity, whether by contract or 20 | otherwise, or (ii) ownership of fifty percent (50%) or more of the 21 | outstanding shares, or (iii) beneficial ownership of such entity. 22 | 23 | "You" (or "Your") shall mean an individual or Legal Entity 24 | exercising permissions granted by this License. 25 | 26 | "Source" form shall mean the preferred form for making modifications, 27 | including but not limited to software source code, documentation 28 | source, and configuration files. 29 | 30 | "Object" form shall mean any form resulting from mechanical 31 | transformation or translation of a Source form, including but 32 | not limited to compiled object code, generated documentation, 33 | and conversions to other media types. 34 | 35 | "Work" shall mean the work of authorship, whether in Source or 36 | Object form, made available under the License, as indicated by a 37 | copyright notice that is included in or attached to the work 38 | (an example is provided in the Appendix below). 39 | 40 | "Derivative Works" shall mean any work, whether in Source or Object 41 | form, that is based on (or derived from) the Work and for which the 42 | editorial revisions, annotations, elaborations, or other modifications 43 | represent, as a whole, an original work of authorship. For the purposes 44 | of this License, Derivative Works shall not include works that remain 45 | separable from, or merely link (or bind by name) to the interfaces of, 46 | the Work and Derivative Works thereof. 47 | 48 | "Contribution" shall mean any work of authorship, including 49 | the original version of the Work and any modifications or additions 50 | to that Work or Derivative Works thereof, that is intentionally 51 | submitted to Licensor for inclusion in the Work by the copyright owner 52 | or by an individual or Legal Entity authorized to submit on behalf of 53 | the copyright owner. For the purposes of this definition, "submitted" 54 | means any form of electronic, verbal, or written communication sent 55 | to the Licensor or its representatives, including but not limited to 56 | communication on electronic mailing lists, source code control systems, 57 | and issue tracking systems that are managed by, or on behalf of, the 58 | Licensor for the purpose of discussing and improving the Work, but 59 | excluding communication that is conspicuously marked or otherwise 60 | designated in writing by the copyright owner as "Not a Contribution." 61 | 62 | "Contributor" shall mean Licensor and any individual or Legal Entity 63 | on behalf of whom a Contribution has been received by Licensor and 64 | subsequently incorporated within the Work. 65 | 66 | 2. Grant of Copyright License. Subject to the terms and conditions of 67 | this License, each Contributor hereby grants to You a perpetual, 68 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 69 | copyright license to reproduce, prepare Derivative Works of, 70 | publicly display, publicly perform, sublicense, and distribute the 71 | Work and such Derivative Works in Source or Object form. 72 | 73 | 3. Grant of Patent License. Subject to the terms and conditions of 74 | this License, each Contributor hereby grants to You a perpetual, 75 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 76 | (except as stated in this section) patent license to make, have made, 77 | use, offer to sell, sell, import, and otherwise transfer the Work, 78 | where such license applies only to those patent claims licensable 79 | by such Contributor that are necessarily infringed by their 80 | Contribution(s) alone or by combination of their Contribution(s) 81 | with the Work to which such Contribution(s) was submitted. If You 82 | institute patent litigation against any entity (including a 83 | cross-claim or counterclaim in a lawsuit) alleging that the Work 84 | or a Contribution incorporated within the Work constitutes direct 85 | or contributory patent infringement, then any patent licenses 86 | granted to You under this License for that Work shall terminate 87 | as of the date such litigation is filed. 88 | 89 | 4. Redistribution. You may reproduce and distribute copies of the 90 | Work or Derivative Works thereof in any medium, with or without 91 | modifications, and in Source or Object form, provided that You 92 | meet the following conditions: 93 | 94 | (a) You must give any other recipients of the Work or 95 | Derivative Works a copy of this License; and 96 | 97 | (b) You must cause any modified files to carry prominent notices 98 | stating that You changed the files; and 99 | 100 | (c) You must retain, in the Source form of any Derivative Works 101 | that You distribute, all copyright, patent, trademark, and 102 | attribution notices from the Source form of the Work, 103 | excluding those notices that do not pertain to any part of 104 | the Derivative Works; and 105 | 106 | (d) If the Work includes a "NOTICE" text file as part of its 107 | distribution, then any Derivative Works that You distribute must 108 | include a readable copy of the attribution notices contained 109 | within such NOTICE file, excluding those notices that do not 110 | pertain to any part of the Derivative Works, in at least one 111 | of the following places: within a NOTICE text file distributed 112 | as part of the Derivative Works; within the Source form or 113 | documentation, if provided along with the Derivative Works; or, 114 | within a display generated by the Derivative Works, if and 115 | wherever such third-party notices normally appear. The contents 116 | of the NOTICE file are for informational purposes only and 117 | do not modify the License. You may add Your own attribution 118 | notices within Derivative Works that You distribute, alongside 119 | or as an addendum to the NOTICE text from the Work, provided 120 | that such additional attribution notices cannot be construed 121 | as modifying the License. 122 | 123 | You may add Your own copyright statement to Your modifications and 124 | may provide additional or different license terms and conditions 125 | for use, reproduction, or distribution of Your modifications, or 126 | for any such Derivative Works as a whole, provided Your use, 127 | reproduction, and distribution of the Work otherwise complies with 128 | the conditions stated in this License. 129 | 130 | 5. Submission of Contributions. Unless You explicitly state otherwise, 131 | any Contribution intentionally submitted for inclusion in the Work 132 | by You to the Licensor shall be under the terms and conditions of 133 | this License, without any additional terms or conditions. 134 | Notwithstanding the above, nothing herein shall supersede or modify 135 | the terms of any separate license agreement you may have executed 136 | with Licensor regarding such Contributions. 137 | 138 | 6. Trademarks. This License does not grant permission to use the trade 139 | names, trademarks, service marks, or product names of the Licensor, 140 | except as required for reasonable and customary use in describing the 141 | origin of the Work and reproducing the content of the NOTICE file. 142 | 143 | 7. Disclaimer of Warranty. Unless required by applicable law or 144 | agreed to in writing, Licensor provides the Work (and each 145 | Contributor provides its Contributions) on an "AS IS" BASIS, 146 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or 147 | implied, including, without limitation, any warranties or conditions 148 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A 149 | PARTICULAR PURPOSE. You are solely responsible for determining the 150 | appropriateness of using or redistributing the Work and assume any 151 | risks associated with Your exercise of permissions under this License. 152 | 153 | 8. Limitation of Liability. In no event and under no legal theory, 154 | whether in tort (including negligence), contract, or otherwise, 155 | unless required by applicable law (such as deliberate and grossly 156 | negligent acts) or agreed to in writing, shall any Contributor be 157 | liable to You for damages, including any direct, indirect, special, 158 | incidental, or consequential damages of any character arising as a 159 | result of this License or out of the use or inability to use the 160 | Work (including but not limited to damages for loss of goodwill, 161 | work stoppage, computer failure or malfunction, or any and all 162 | other commercial damages or losses), even if such Contributor 163 | has been advised of the possibility of such damages. 164 | 165 | 9. Accepting Warranty or Additional Liability. While redistributing 166 | the Work or Derivative Works thereof, You may choose to offer, 167 | and charge a fee for, acceptance of support, warranty, indemnity, 168 | or other liability obligations and/or rights consistent with this 169 | License. However, in accepting such obligations, You may act only 170 | on Your own behalf and on Your sole responsibility, not on behalf 171 | of any other Contributor, and only if You agree to indemnify, 172 | defend, and hold each Contributor harmless for any liability 173 | incurred by, or claims asserted against, such Contributor by reason 174 | of your accepting any such warranty or additional liability. 175 | 176 | END OF TERMS AND CONDITIONS 177 | 178 | APPENDIX: How to apply the Apache License to your work. 179 | 180 | To apply the Apache License to your work, attach the following 181 | boilerplate notice, with the fields enclosed by brackets "[]" 182 | replaced with your own identifying information. (Don't include 183 | the brackets!) The text should be enclosed in the appropriate 184 | comment syntax for the file format. We also recommend that a 185 | file or class name and description of purpose be included on the 186 | same "printed page" as the copyright notice for easier 187 | identification within third-party archives. 188 | 189 | Copyright [yyyy] [name of copyright owner] 190 | 191 | Licensed under the Apache License, Version 2.0 (the "License"); 192 | you may not use this file except in compliance with the License. 193 | You may obtain a copy of the License at 194 | 195 | http://www.apache.org/licenses/LICENSE-2.0 196 | 197 | Unless required by applicable law or agreed to in writing, software 198 | distributed under the License is distributed on an "AS IS" BASIS, 199 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 200 | See the License for the specific language governing permissions and 201 | limitations under the License. 202 | --------------------------------------------------------------------------------