v4.09

pola-rs/polarsv4.09Aug 7, 2026by jianchang512

AI Summary

A Windows release adding support for new TTS/ASR models, fixing Whisper errors, and introducing speaker diarization.

Key Highlights

  • Supports Index-TTS 2.5.
  • Fixes Faster_whisper_xxl.exe errors.
  • Adds Moss-Transcribe-Diarize model for speaker identification in audio/video.
  • Adds new ASR models: Audio8/ARK-ASR-0.6B and ibm-granite/granite-speech-4.1-2b.
  • Adds higgs-audio-v3-tts-4b model with CUDA acceleration support.
  • Adds Vietnamese and Turkish language support to F5-TTS.

New Features

  • New TTS and ASR model support.
  • Speaker diarization integration.
  • Bug fixes for Whisper and translation prompts.
  • Restored local subtitle import button.

Full Release Notes

## v4.09 Change log

> MacOX / Linux 请使用源码部署


**v4.09更新日志**

- 支持 index-tts 2.5 
- 修复 Faster_whisper_xxl.exe 报错
- 优化字幕翻译提示词
- 恢复导入本地源语言字幕按钮,仅单视频模式下生效
- 微软翻译已无法使用,报错时自动使用本地模型`M2M100(内置)`替换
- 语音识别 增加`Moss-Transcribe-Diarize`模型,90分钟内音视频支持直接返回说话人
- 语音识别 Huggingface_ASR渠道 增加模型`Audio8/ARK-ASR-0.6B` `ibm-granite/granite-speech-4.1-2b`
- 配音渠道增加`higgs-audio-v3-tts-4b`模型,CUDA加速需10G+显存,CPU运行需20G+内存
- F5-TTS 增加 越南语、土耳其语支持
- 修复其他已知bug



----

### v4.09 完整包下载(2.7G)

- 百度网盘地址: https://pan.baidu.com/s/1deSACf5Wmy34Ua8hzgDQVw?pwd=1234
- huggingface.co:  https://huggingface.co/mortimerme/repocollect/resolve/main/win-pyvideotrans-v4.09-0816.7z?download=true


### v4.09 补丁包下载(300MB)

> 补丁包不可单独使用,仅用于覆盖旧包, 覆盖后如果闪退或报错,请下载完整包。

- 百度网盘地址: https://pan.baidu.com/s/1GPBXPSSbNdUk9hUKIPjQZQ?pwd=1234
- huggingface.co: https://huggingface.co/mortimerme/repocollect/resolve/main/win-PatchUpdate-v4.09-0816.7z?download=true


**Full Changelog**: https://github.com/jianchang512/pyvideotrans/compare/v4.08...v4.09