AutoDownloadChatGPTVoice
Description
TTS (Text-to-Speech) via ChatGPT. Automatically downloads the audio file when ChatGPT's read aloud button is clicked.
通过ChatGPT实现文本转语音(当播放chatgpt的朗读时，自动将声音文件下载下来)
Overview
When you ask ChatGPT to read a piece of text, it does so with a very natural and fluent voice, and you can even adjust its tone during the conversation. This makes ChatGPT an excellent TTS(text-to-speech) tool. However, OpenAI does not provide a way to download the audio file (even if you ask ChatGPT to send the audio as a file), which is where the AutoDownloadChatGPTVoice script comes in. This Tampermonkey script is designed to capture the request data when you click the read-aloud button below the ChatGPT text, decode it, and convert it into a .aac file for download.
当你尝试让 ChatGPT 朗读一段话时，它会以非常自然流畅的声音朗读出来，你甚至可以在对话中调整它的情绪，这使得 ChatGPT 成为了一个很好的文本转语音工具。然而，OpenAI 并没有提供语音文件的下载方式（即使你要求 ChatGPT 将语音以文件形式发送），所以 AutoDownloadChatGPTVoice 脚本应运而生。这个油猴脚本被设计为当你点击 ChatGPT 文本下方的朗读按钮时，可以捕获请求数据，并将其解码转换成 .aac 文件下载到本地。
Installation
- Make sure you have installed the Tampermonkey extension.
- Download the
fetchResponseDownloader.user.js file.
- Open the Tampermonkey dashboard and click "Create a new script".
- Paste the content of the
fetchResponseDownloader.user.js file into the editor and save it.
- 确保你已经安装了 Tampermonkey 扩展.
- 下载
fetchResponseDownloader.user.js 文件.
- 打开 Tampermonkey 仪表板，点击“添加新脚本”.
- 将
fetchResponseDownloader.user.js 文件的内容粘贴到编辑器中，然后保存.
Usage
During a conversation with ChatGPT, a speaker button (![SVG Image]()
) will appear below the text.
Clicking the speaker button ![SVG Image]()
will trigger the script to automatically download the audio file to your local device.
在与 ChatGPT 的对话中，文本下方会出现一个扬声器按钮（![SVG Image]()
).
点击扬声器按钮 ![SVG Image]()
后脚本就会自动下载语音文件到本地.
