v4.13
jianchang512/pyvideotransv4.13Sep 20, 2026by jianchang512
Upgrading?
AI Summary
This release introduces a Windows pre-packaged version for easier deployment. Key updates include optimizations to the Whisper model recognition and segmentation algorithms, expanded support for external AI providers like SiliconFlow and Minimax, and new characters for Doubao 2.0 voice synthesis. The interface has also been refactored to simplify the process of adding new channels.
Key Highlights
- Windows pre-packaged version (2.7G) available for download
- Enhanced support for SiliconFlow, Minimax, and OpenRouter providers
- Optimized Whisper model recognition and segmentation algorithms
- Refactored settings window and menu architecture
- Added a pause button to the media merging function
New Features
- API Route provider support added
- Doubao 2.0 voice synthesis now includes new dubbing roles
- Media merging function now includes a pause button
- Sensitive tokens (Baidu secret, Doubao access token) are masked in logs
- Plain text handling for subtitles without timestamps
- Short subtitle fractions are read as decimals
Full Release Notes
## v4.13 Win10/11 预打包版本下载 <details> <summary>MacOS/Linux系统请使用源码部署</summary> 1. 安装依赖: ```bash # macOS brew install libsndfile git brew tap homebrew-ffmpeg/ffmpeg brew install homebrew-ffmpeg/ffmpeg/ffmpeg # Ubuntu/Debian sudo apt-get install ffmpeg libsndfile1-dev ``` 3. 安装 uv: ```bash curl -LsSf https://astral.sh/uv/install.sh | sh ``` 4. 克隆并启动: ```bash git clone https://github.com/jianchang512/pyvideotrans.git cd pyvideotrans uv sync uv run sp.py ``` </details> ### 更新日志/Changelos - 优化模型下载处理,失败后将自动重试 - 优化 whisper 模型识别后重断句算法 - 硅基流动、Minimax、OpenRouter 完善 语音识别/字幕翻译/语音合成 模型支持 - 豆包语音合成2.0 新增配音角色 - 重构 设置窗口、菜单架构,简化新增渠道 - Qwen-TTS/Higgs等本地配音渠道放弃8位量化,避免某些环境下兼容问题 - 媒体合并 功能里增加暂停按钮 #1208 - 修复其他已知bug ---- ### v4.13 完整包下载(2.7G) - 百度网盘地址: https://pan.baidu.com/s/1Ff__zBpMAVKJE-7A9t-a7w?pwd=1234 - huggingface.co: https://huggingface.co/mortimerme/repocollect/resolve/main/win-pyvideotrans-v4.13-1.7z?download=true ### v4.13 补丁包下载(360MB) > 补丁包不可单独使用,仅用于覆盖旧包, 如果版本相差较多,请直接下载完整包,勿使用补丁包。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/18NR-AKfPPNje5wpHEB2wSQ?pwd=1234 - huggingface.co: https://huggingface.co/mortimerme/repocollect/resolve/main/win-PatchUpdate-v4.13.7z?download=true ---- <details><summary>解压注意事项</summary> - 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://bandisoft.com/bandizip/) 或 [360压缩软件](https://yasuo.360.cn) 进行解压 </details> ---- <details><summary> 如果新版遇到问题可继续使用上个版本(v4.12/v4.03)</summary> **v4.12 完整包下载(2.7G)** - 百度网盘地址: https://pan.baidu.com/s/11LKtD3l5Ti-H2DprXRqNrg?pwd=1234 - huggingface.co: https://huggingface.co/mortimerme/repocollect/resolve/main/win-pyvideotrans-v4.12-0913.7z?download=true **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 **v4.03 完整包下载(2.7G)** - 百度网盘地址: https://pan.baidu.com/s/1yENT4t7E5K1OrbOFS7WEvA?pwd=1234 - huggingface.co: https://huggingface.co/mortimerme/repocollect/resolve/main/win-pyvideotrans-v4.03-0626.7z?download=true </details> ---- ## What's Changed * fix: raise NotImplementedError instead of NotImplemented in the three abstract stubs by @Anai-Guo in https://github.com/jianchang512/pyvideotrans/pull/1197 * feat(translator): add API Route provider support by @DennyHo0917 in https://github.com/jianchang512/pyvideotrans/pull/1205 * Keep the case of custom API URLs (translate, TTS, STT) by @Dev-next-gen in https://github.com/jianchang512/pyvideotrans/pull/1207 * Mask the Baidu secret and Doubao access token in logs by @Dev-next-gen in https://github.com/jianchang512/pyvideotrans/pull/1211 * Keep plain text intact when a subtitle file has no timestamps by @Dev-next-gen in https://github.com/jianchang512/pyvideotrans/pull/1210 * Check the LibreTranslate column when validating the target language by @Dev-next-gen in https://github.com/jianchang512/pyvideotrans/pull/1209 * Read short subtitle fractions as decimals by @Dev-next-gen in https://github.com/jianchang512/pyvideotrans/pull/1212 ## New Contributors * @Anai-Guo made their first contribution in https://github.com/jianchang512/pyvideotrans/pull/1197 * @DennyHo0917 made their first contribution in https://github.com/jianchang512/pyvideotrans/pull/1205 * @Dev-next-gen made their first contribution in https://github.com/jianchang512/pyvideotrans/pull/1207 **Full Changelog**: https://github.com/jianchang512/pyvideotrans/compare/v4.12...v4.13
Related Repositories
A collective list of free APIs
The agent that grows with you
A feature-rich command-line audio/video downloader
Python tool for converting files and office documents to Markdown.
AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.