[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-2659":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":10,"totalLinesOfCode":10,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":16,"subscribersCount":16,"size":16,"stars1d":17,"stars7d":18,"stars30d":19,"stars90d":16,"forks30d":16,"starsTrendScore":20,"compositeScore":21,"rankGlobal":10,"rankLanguage":10,"license":22,"archived":23,"fork":23,"defaultBranch":24,"hasWiki":23,"hasPages":23,"topics":25,"createdAt":10,"pushedAt":10,"updatedAt":29,"readmeContent":30,"aiSummary":31,"trendingCount":16,"starSnapshotCount":16,"syncStatus":32,"lastSyncTime":33,"discoverSource":34},2659,"pyvideotrans","jianchang512\u002Fpyvideotrans","jianchang512","Translate the video from one language to another and embed dubbing & subtitles.","https:\u002F\u002Fpyvideotrans.com",null,"Python",17916,2230,104,32,0,8,129,545,60,45,"GNU General Public License v3.0",false,"main",[26,27,28],"speech-to-text","text-to-speech","video-transition","2026-06-12 02:00:42","\n> Sponsors: **[Recall.ai](https:\u002F\u002Fwww.recall.ai\u002Fproduct\u002Fmeeting-transcription-api?utm_source=github&utm_medium=sponsorship&utm_campaign=jianchang512-pyvideotrans) - Meeting Transcription API**\n>\n> If you’re looking for a transcription API for meetings, consider checking out **[Recall.ai](https:\u002F\u002Fwww.recall.ai\u002Fproduct\u002Fmeeting-transcription-api?utm_source=github&utm_medium=sponsorship&utm_campaign=jianchang512-pyvideotrans)** , an API that works with Zoom, Google Meet, Microsoft Teams, and more\n\n\n\n\n# pyVideoTrans \n\n\u003Cdiv align=\"center\">\n\n**A Powerful Open Source Video Translation \u002F Audio Transcription \u002F AI Dubbing \u002F Subtitle Translation Tool**\n\n[中文](docs\u002FREADME_CN.md) | [**Documentation**](https:\u002F\u002Fpyvideotrans.com) | [**Online Q&A**](https:\u002F\u002Fbbs.pyvideotrans.com)\n\n[![License](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLicense-GPL_v3-blue.svg)](LICENSE)   [![Python](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FPython-3.10%2B-green.svg)](https:\u002F\u002Fwww.python.org\u002F)   [![Platform](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FPlatform-Windows%20%7C%20macOS%20%7C%20Linux-lightgrey.svg)]()\n\n\u003C\u002Fdiv>\n\n**pyVideoTrans** is dedicated to seamlessly converting videos from one language to another, offering a complete workflow that includes speech recognition, subtitle translation, multi-role dubbing, and audio-video synchronization. It supports both local offline deployment and a wide variety of mainstream online APIs.\n\n\u003Cimg width=\"1658\" height=\"935\" alt=\"image\" src=\"https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002Fc5959e59-6014-480c-9a7d-44c2b1729d36\" \u002F>\n\n---\n\n## ✨ Core Features\n\n- **🎥 Fully Automatic Video Translation**: One-click workflow: Speech Recognition (ASR) -> Subtitle Translation -> Speech Synthesis (TTS) -> Video Synthesis.\n- **🎙️ Audio Transcription \u002F Subtitle Generation**: Batch convert audio\u002Fvideo to SRT subtitles, supporting **Speaker Diarization** to distinguish between different roles.\n- **🗣️ Multi-Role AI Dubbing**: Assign different AI dubbing voices to different speakers.\n- **🧬 Voice Cloning**: Integrates models like **F5-TTS, CosyVoice, GPT-SoVITS** for zero-shot voice cloning.\n- **🧠 Powerful Model Support**: \n  - **ASR**: Faster-Whisper (Local), OpenAI Whisper, Alibaba Qwen, ByteDance Volcano, Azure, Google, etc.\n  - **LLM Translation**: DeepSeek, ChatGPT, Claude, Gemini, MiniMax, Ollama (Local), Alibaba Bailian, etc.\n  - **TTS**: Edge-TTS (Free), OpenAI, Azure, Minimaxi, ChatTTS, ChatterBox, etc.\n- **🖥️ Interactive Editing**: Supports pausing and manual proofreading at each stage (recognition, translation, dubbing) to ensure accuracy.\n- **🛠️ Utility Toolkit**: Includes auxiliary tools such as vocal separation, video\u002Fsubtitle merging, audio-video alignment, and transcript matching.\n- **💻 Command Line Interface (CLI)**: Supports headless operation, convenient for server deployment or batch processing.\n\n\u003Cimg width=\"2752\" height=\"1536\" alt=\"unnamed\" src=\"https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002F960e9e34-84a4-425d-b582-f726623475a8\" \u002F>\n\n---\n\n## 🚀 Quick Start (Windows Users)\n\nWe provide a pre-packaged `.exe` version for Windows 10\u002F11 users, requiring no Python environment configuration.\n\n1. **Download**: [Click to download the latest pre-packaged version](https:\u002F\u002Fgithub.com\u002Fjianchang512\u002Fpyvideotrans\u002Freleases)\n2. **Unzip**: Extract the compressed file to a path (e.g., `D:\\pyVideoTrans`).\n3. **Run**: Double-click `sp.exe` inside the folder to launch.\n\n> **Note**: \n> *   Do not run directly from within the compressed archive.\n> *   To use GPU acceleration, ensure **CUDA 12.8** and **cuDNN 9.11** are installed.\n\n---\n\n## 🛠️ Source Deployment (macOS \u002F Linux \u002F Windows Developers)\n\nWe recommend using **[`uv`](https:\u002F\u002Fdocs.astral.sh\u002Fuv\u002F)** for package management for faster speed and better environment isolation.\n\n### 1. Prerequisites\n\n*   **Python**: Recommended version 3.10 --> 3.12\n*   **FFmpeg**: Must be installed and configured in the environment variables.\n    *   **macOS**: `brew install ffmpeg libsndfile git`\n    *   **Linux (Ubuntu\u002FDebian)**: `sudo apt-get install ffmpeg libsndfile1-dev`\n    *   **Windows**: [Download FFmpeg](https:\u002F\u002Fffmpeg.org\u002Fdownload.html) and configure Path, or place `ffmpeg.exe` and `ffprobe.exe` directly in the project directory.\n\n### 2. Install uv (If not installed)\n\n```bash\n# macOS\u002FLinux\ncurl -LsSf https:\u002F\u002Fastral.sh\u002Fuv\u002Finstall.sh | sh\n\n# Windows (PowerShell)\npowershell -c \"irm https:\u002F\u002Fastral.sh\u002Fuv\u002Finstall.ps1 | iex\"\n```\n\n### 3. Clone and Install\n\n```bash\n# 1. Clone the repository (Ensure path has no spaces\u002FChinese characters)\ngit clone https:\u002F\u002Fgithub.com\u002Fjianchang512\u002Fpyvideotrans.git\ncd pyvideotrans\n\n# 2. Install dependencies (uv automatically syncs environment)\nuv sync\n\n# If you need local channels for qwen-tts and qwen-asr, please execute `uv sync --extra qwen-tts --extra qwen-asr`\n\n```\n\n### 4. Launch Software\n\n**Launch GUI**:\n```bash\nuv run sp.py\n```\n\n**Use CLI**:\n\n> [View documentation for detailed parameters](https:\u002F\u002Fpyvideotrans.com\u002Fcli)\n\n```bash\n# Video Translation Example\nuv run cli.py --task vtv --name \".\u002Fvideo.mp4\" --source_language_code zh --target_language_code en\n\n# Audio to Subtitle Example\nuv run cli.py --task stt --name \".\u002Faudio.wav\" --model_name large-v3\n```\n\n### 5. (Optional) GPU Acceleration Configuration\n\nIf you have an NVIDIA graphics card, execute the following commands to install the CUDA-supported PyTorch version:\n\n```bash\n# Uninstall CPU version\nuv remove torch torchaudio\n\n# Install CUDA version (Example for CUDA 12.x)\nuv add torch==2.7 torchaudio==2.7 --index-url https:\u002F\u002Fdownload.pytorch.org\u002Fwhl\u002Fcu128\nuv add nvidia-cublas-cu12 nvidia-cudnn-cu12\n```\n\n---\n\n## 🧩 Supported Channels & Models (Partial)\n\n| Category | Channel\u002FModel | Description |\n| :--- | :--- | :--- |\n| **ASR (Speech Recognition)** | **Faster-Whisper** (Local) | Recommended, fast speed, high accuracy |\n| | WhisperX \u002F Parakeet | Supports timestamp alignment & speaker diarization |\n| | Alibaba Qwen3-ASR \u002F ByteDance Volcano | Online API, excellent for Chinese |\n| **Translation (LLM\u002FMT)** | **DeepSeek** \u002F ChatGPT | Supports context understanding, more natural translation |\n| | MiniMax AI | MiniMax M2.7 LLM, latest flagship model, OpenAI-compatible |\n| | Google \u002F Microsoft | Traditional machine translation, fast speed |\n| | Ollama \u002F M2M100 | Fully local offline translation |\n| **TTS (Speech Synthesis)** | **Edge-TTS** | Microsoft free interface, natural effect |\n| | **F5-TTS \u002F CosyVoice** | Supports **Voice Cloning**, requires local deployment |\n| | GPT-SoVITS \u002F ChatTTS | High-quality open-source TTS |\n| | 302.AI \u002F OpenAI \u002F Azure | High-quality commercial API |\n\n---\n\n## 📚 Documentation & Support\n\n*   **Official Documentation**: [https:\u002F\u002Fpyvideotrans.com](https:\u002F\u002Fpyvideotrans.com) (Includes detailed tutorials, API configuration guides, FAQ)\n*   **Online Q&A Community**: [https:\u002F\u002Fbbs.pyvideotrans.com](https:\u002F\u002Fbbs.pyvideotrans.com) (Submit error logs for automated AI analysis and answers)\n\n## ⚠️ Disclaimer\n\nThis software is an open-source, free, non-commercial project. Users are solely responsible for any legal consequences arising from the use of this software (including but not limited to calling third-party APIs or processing copyrighted video content). Please comply with local laws and regulations and the terms of use of relevant service providers.\n\n## 🙏 Acknowledgements\n\nThis project mainly relies on the following open-source projects (partial):\n\n*   [FFmpeg](https:\u002F\u002Fgithub.com\u002FFFmpeg\u002FFFmpeg)\n*   [PySide6](https:\u002F\u002Fpypi.org\u002Fproject\u002FPySide6\u002F)\n*   [faster-whisper](https:\u002F\u002Fgithub.com\u002FSYSTRAN\u002Ffaster-whisper)\n*   [openai-whisper](https:\u002F\u002Fgithub.com\u002Fopenai\u002Fwhisper)\n*   [edge-tts](https:\u002F\u002Fgithub.com\u002Frany2\u002Fedge-tts)\n*   [F5-TTS](https:\u002F\u002Fgithub.com\u002FSWivid\u002FF5-TTS)\n*   [CosyVoice](https:\u002F\u002Fgithub.com\u002FFunAudioLLM\u002FCosyVoice)\n\n---\n\n*Created by [jianchang512](https:\u002F\u002Fgithub.com\u002Fjianchang512)*","pyVideoTrans 是一个强大的开源视频翻译工具，能够将视频从一种语言转换为另一种语言，并嵌入配音和字幕。其核心功能包括全自动视频翻译、音频转录\u002F字幕生成、多角色AI配音以及语音克隆等。该工具支持多种主流在线API及本地离线部署，适用于需要跨语言内容转换的场景，如跨国教育资料制作、影视作品本地化等。通过集成先进的ASR（自动语音识别）、LLM（大型语言模型）翻译和TTS（文本转语音）技术，pyVideoTrans 提供了从语音识别到最终视频合成的一站式解决方案，同时具备交互式编辑能力以确保输出质量。",2,"2026-06-11 02:50:38","top_language"]