Starstruk Logo MarkStarstruk

v3.59

jianchang512/pyvideotransv3.59Feb 28, 2025by jianchang512

AI Summary

Integrated ElevenLabs for speech recognition and added Minimaxi TTS support.

Key Highlights

  • Added Elevenlabs.io as a new speech recognition channel.
  • Added Minimaxi TTS support in the custom API section.
  • Fixed ElevenLabs.io TTS functionality.

New Features

  • Elevenlabs.io speech recognition
  • Minimaxi TTS support

Full Release Notes

> 预打包版仅适用于Windows10/11，MacOS和Linux请源码部署
> MacOS/Linux升级：重新拉取源码覆盖，然后执行
>  `pip3 install --upgrade openai-whisper elevenlabs` 
>  `pip3 install --no-deps  --force-reinstall "faster-whisper @ https://github.com/SYSTRAN/faster-whisper/archive/refs/heads/master.tar.gz"`

## Change

- Feat: 在自定义TTS API 中接入 Minimaxi 配音，文档 https://pvt9.com/minimaxi
- Fix: #751 #671 
- Fix: elevenlabs.io TTS
- Feat: 语音识别新增`Elevenlabs.io`渠道，来自 [11ElevenLabs scribe_v1模型](https://elevenlabs.io/docs/api-reference/speech-to-text/convert)


## Win v3.59 完整包下载

> 如果未安装过旧版本，请在此下载完整版，如需cuda加速，需有英伟达显卡并且安装cuda12.x及cudnn9

百度网盘下载地址(含tiny/medium模型):  https://pan.baidu.com/s/1oh9oxrMlGIlTywbAtIHIxQ?pwd=sa9j

GitHub地址: https://github.com/jianchang512/pyvideotrans/releases/download/v3.59/win-videotrans-v3.59-tiny.7z

 

## v3.63 补丁包190MB

> 如果已安装过3.x版本，可下载补丁包后解压在sp.exe所在目录，覆盖已有sp.exe和文件夹

百度网盘下载地址: https://pan.baidu.com/s/1F3hmCpPxSs0X8qAnWfI_UA?pwd=im7f

GitHub地址: https://github.com/jianchang512/pyvideotrans/releases/download/v3.59/win-PatchUpdate-3.63.7z


> 若补丁覆盖后打开提示`需下载完整包`，请升级显卡驱动、升级cuda到12.x、升级cudnn到cudnn9，并重新下载完整包


----

### 所有模型下载地址

为避免压缩包体积过大，预打包版只内置最小模型 tiny，识别效果不佳，效果更好的模型请点击下载 ，建议至少使用medium模型，推荐large-v2

https://github.com/jianchang512/stt/releases/tag/0.0