v4.16
jianchang512/pyvideotransv4.16Oct 13, 2026by jianchang512
Upgrading?
AI Summary
This release introduces new translation channels (Atlas Cloud, audio.cpp backend, and fish.audio API), fixes Edge-TTS 403 errors, and adds a new LLM feature for sentence segmentation alongside French localization.
Key Highlights
- Added three new translation channels: Atlas Cloud, audio.cpp backend, and fish.audio API.
- Fixed Edge-TTS 403 error for Mac/Linux/Source builds requiring a specific update command.
- Introduced a new 'Use LLM to re-segment sentences' option in advanced settings.
- Added French interface localization support.
- Normalized parameter names in params.json.
Breaking Changes
- Parameter names in params.json have been normalized, potentially requiring users to re-enter API keys and addresses.
New Features
- Atlas Cloud translation channel
- audio.cpp backend support
- fish.audio API support
- LLM sentence segmentation feature
- French interface localization
Full Release Notes
## v4.16 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> **Changelog** - 修复 Edge-TTS 403问题,Macos和linux或windows源码部署版本,请执行命令更新`uv add git+https://github.com/rany2/edge-tts.git`,若出错,则先执行`uv remove edge-tts` 后再重新更新 - 增加 配音渠道 [audio.cpp 后端](/audiocpp) - 增加 配音渠道 [fish.audio api](/fishaudioapi) 支持 - 规范化 params.json 中参数名称,某些渠道的SK、api地址等信息,在更新后可能需要重新填写 - 高级选项`字幕翻译`增加`使用LLM重新断句替代LLM纠错`,若选中该项及`LLM纠错`,将在语音识别后一次性将识别结果提交给AI模型重新断句和修正错误 - 修复已知bug * feat(translator): add Atlas Cloud translation channel / 新增 Atlas Cloud 翻译渠道 by @binyangzhu000-sudo in https://github.com/jianchang512/pyvideotrans/pull/1222 * feat(webui): add French interface localization by @didlawowo in https://github.com/jianchang512/pyvideotrans/pull/1204 * New Contributors * @binyangzhu000-sudo made their first contribution in https://github.com/jianchang512/pyvideotrans/pull/1222 * @didlawowo made their first contribution in https://github.com/jianchang512/pyvideotrans/pull/1204 **Full Changelog**: https://github.com/jianchang512/pyvideotrans/compare/v4.15...v4.16 ---- ### v4.16 完整包下载(2.7G) - 百度网盘地址: https://pan.baidu.com/s/1XlK6dvf-4UoiWvjtEtqaAg?pwd=1234 - huggingface.co: https://huggingface.co/mortimerme/repocollect/resolve/main/win-pyvideotrans-v4.16.7z?download=true ### v4.16 补丁包下载(390MB) > 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/1_pBNI9tnW-ZwauHVg-6lJA?pwd=1234 - huggingface.co: https://huggingface.co/mortimerme/repocollect/resolve/main/win-PatchUpdate-v4.16.7z?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(v4.14/v4.03)</summary> **v4.14 完整包下载(2.7G)** - 百度网盘地址: https://pan.baidu.com/s/1nPX5v_kqcOUzaqk9Zu33PA?pwd=1234 - huggingface.co: https://huggingface.co/mortimerme/repocollect/resolve/main/win-pyvideotrans-v4.14.7z?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> ----
Related Repositories
public-apis/public-apis★ 491,133
A collective list of free APIs
NousResearch/hermes-agent★ 255,942
The agent that grows with you
yt-dlp/yt-dlp★ 200,043
A feature-rich command-line audio/video downloader
microsoft/markitdown★ 191,490
Python tool for converting files and office documents to Markdown.
Significant-Gravitas/AutoGPT★ 187,702
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.