V4.01

aws-samples/bedrock-chatV4.01Jun 2, 2026by jianchang512

AI Summary

This version integrates the Chatterbox engine and upgrades the default MiniMax model to M3, while removing the gTTS option and fixing several stability issues across TTS engines.

Key Highlights

  • Chatterbox engine built-in
  • MiniMax-M3 model upgrade
  • Bug fixes for Qwen-TTS and GPT-SoVITS
  • Removal of gTTS dubbing channel

Breaking Changes

  • Remove gTTS dubbing channel

New Features

  • Chatterbox integration
  • MiniMax-M3 upgrade
  • Exception handling improvements

Full Release Notes

**v4.01更新日志**

- chatterbox 改为内置
- 修复几处bug(qwen-tts/gpt-sovits/openai)
- 移除 gTTS 配音渠道


----

##  v4.01 完整包下载(2.6G)


百度网盘地址: https://pan.baidu.com/s/1xxFCgXLds1IFT7pzxFDvfQ?pwd=1234

huggingface.co:  https://huggingface.co/mortimerme/repocollect/resolve/main/win-pyvideotrans-v4.01-0602.7z?download=true


### v4.01 补丁包下载(260MB)

> 补丁包不可单独使用,仅用于覆盖旧包,与完整包区别是不含有`torch`模块
> 因torch从 2.5 升级到 2.7,补丁包不含有torch,直接下载覆盖补丁包可能导致无法cuda加速,建议下载完整包覆盖
> **覆盖后如果闪退,请下载完整包**

百度网盘地址: https://pan.baidu.com/s/1yABsqNpwTtgjPhgyG27DvA?pwd=1234

huggingface.co: https://huggingface.co/mortimerme/repocollect/resolve/main/win-PatchUpdate-v4.01-0602.7z?download=true



----

----

## 历史版本下载

- 百度网盘地址: https://pan.baidu.com/s/18cjXewsWNt4QGGfp6q_14g?pwd=1234
- GitHub地址: https://github.com/jianchang512/pyvideotrans/releases
- 相关TTS整合包下载: https://pan.baidu.com/s/1s2ThLXj39-6HbBOo62uXcw?pwd=1234

----

**解压注意事项:**

- 解压7z压缩包,解压后,找到 `sp.exe` 文件,双击即可启动软件,不可在压缩包内双击运行。
- 不要将软件解压到桌面或 C 盘的 `Program Files` 等需要管理员权限的文件夹下。
- 避免路径错误: 解压路径中不要包含中文、空格或特殊符号。
- 如果使用7zip软件解压提示错误,请尝试使用 [Bandizip](https://cn.bandisoft.com/bandizip/) 或 [360压缩软件](https://yasuo.360.cn) 进行解压

## What's Changed
* 修复:3 处 bare except 具体化,防止静默吞噬系统异常 by @zwyin in https://github.com/jianchang512/pyvideotrans/pull/1120
* 修复:崩溃防护 — 3 处空数据/类型守卫防止运行时崩溃 by @zwyin in https://github.com/jianchang512/pyvideotrans/pull/1119
* bug fix: return full source subtitles by @glovebx in https://github.com/jianchang512/pyvideotrans/pull/1122
* feat(minimax): upgrade default model to MiniMax-M3 by @octo-patch in https://github.com/jianchang512/pyvideotrans/pull/1128

## New Contributors
* @glovebx made their first contribution in https://github.com/jianchang512/pyvideotrans/pull/1122

**Full Changelog**: https://github.com/jianchang512/pyvideotrans/compare/v4.00...V4.01