v3.74
jianchang512/pyvideotransv3.74Jul 16, 2025by jianchang512
AI Summary
Windows release brings significant feature additions including new TTS engines, speaker identification, new translation channels, and multi-role dubbing capabilities.
Key Highlights
- Added Qwen-TTS and multi-role dubbing features
- Added new translation channels (ZhipuAI, DeepSeek, Siliconflow, OpenRouter)
- Added speaker identification for Ali/FunASR/Deepgram/Gemini
New Features
- Qwen-TTS
- Multi-role dubbing
- Speaker identification for Ali/FunASR/Deepgram/Gemini
- New translation channels (ZhipuAI, DeepSeek, Siliconflow, OpenRouter)
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 whisper elevenlabs gradio_client faster-whisper` ## Change - Feat: 配音渠道增加 `Qwen-TTS` 详述<https://pvt9.com/qwen-tts> - Fix: #849 - Fix: 音频加速视频慢速同步滞后 - Fix: siliconflow save models error - Feat: `阿里FunASR/Deepgram.com/Gemini大模型识别` 支持说话人识别 - Feat: 新增 `智谱AI/DeepSeek/Siliconflow/OpenRouter.ai` 翻译渠道 - Feat: 新增`字幕多角色配音`功能,可导入srt字幕,单独为每条字幕设定发音角色 - Optim: LLM重新断句可选AI引擎为`OpenAI渠道或DeepSeek`, 在高级选项-通用设置里选择 ## v3.74 完整包下载(1.9G) > 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: https://pan.baidu.com/s/1A6unNnt9BLZIBhdIi3pPnA?pwd=q8qr GitHub地址: https://github.com/jianchang512/pyvideotrans/releases/download/v3.74/win-videotrans-v3.74-0720.7z ## v3.74-0720 补丁包(380MB) > 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 > 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 百度网盘下载地址: https://pan.baidu.com/s/1OIqnIIhnxYMRiPeJCg0v1w?pwd=rxnr GitHub地址: https://github.com/jianchang512/pyvideotrans/releases/download/v3.74/win-PatchUpdate-3.74-0720.7z **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360压缩软件解压(https://yasuo.360.cn)