16 |
17 |
18 |
46 |
47 |
48 |
--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
1 | # openai-workshop
2 |
3 | 
4 |
5 | 這是一個整合OpenAI的練習專案，從text-davinci 到 最新的 Whisper 都有使用。
6 |
7 | This is an integration practice project that uses OpenAI's models from Text-Davinci to the latest Whisper.
8 |
9 | ## 準備
10 | 1. 先到 OpenAI申請一個 API-Key https://platform.openai.com/account/api-keys
11 |
12 | 2. 每一個 Model的費用都不一樣，再使用之前，請先確認 https://openai.com/pricing
13 |
14 | 3. API呼叫是有費用的，可以到Usage去確認用量 https://platform.openai.com/account/usage
15 |
16 | ## Preparation:
17 |
18 | 1. Apply for an API-Key from OpenAI: https://platform.openai.com/account/api-keys
19 |
20 | 2. Each model has different costs. Before using, please check the pricing on https://openai.com/pricing
21 |
22 | 3. There is a cost for API calls. You can check your usage on https://platform.openai.com/account/usage
23 |
24 | ## Step1.html
25 | 使用 text-davinci，輸入一個keyword後，回傳一篇文章的標題
26 |
27 | Using text-davinci model, input a keyword, then response a article titel
28 |
29 | ## Step2.html
30 | text-davinci 價格非常高，所以改使用gpt-3.5。因為API的格式並不一樣，再做微幅修改
31 |
32 | Switched to using GPT-3.5 instead of text-davinci due to the high price. Minor modifications were made to the API format.
33 |
34 | ## Step3.html
35 | 將OpenAI回傳的內容，再為文章產生一張圖片，這邊使用了 DALL.E model
36 |
37 | Generating an image for the article based on the content returned by OpenAI, using the DALL-E model.
38 |
39 | ## Step4.html/Step5.html
40 | 懶人模式，不想打字，改用語音方式輸入關鍵字，將語音傳給OpenAI做解析。
41 |
42 | Lazy mode, don't want to type, switch to voice input to enter keywords, and send the voice to OpenAI for parsing.
43 |
44 | ## Step6.html
45 | OpenAI 新功能 Text-to—Speech，文字轉語音的測試，有6個風格可以使用看看
46 |
47 | OpenAI's new feature Text-to-Speech allows testing of converting text into speech with 6 different styles to explore.
48 |
49 | ## 備註、Note
50 | 在Step4.html/Step5.html時，如果你沒有Local Server，會無法正常的拿到麥克風權限，需要使用 plug-in： Live Server
51 |
52 | During Step4.html/Step5.html, if you do not have a Local Server, you will not be able to obtain microphone permissions properly. You need to use the plug-in Live Server.
53 |
54 | https://marketplace.visualstudio.com/items?itemName=ritwickdey.LiveServer
55 |
--------------------------------------------------------------------------------
/step6.html:
--------------------------------------------------------------------------------
1 |
2 |
3 |
4 |
5 | OpenAI Web Project
6 |
7 |
8 |