About this project

pyVideoTrans is an open-source tool for translating videos from one language to another. It provides a complete workflow: speech recognition (ASR), subtitle translation, speech synthesis (TTS), and video synthesis. It supports local offline deployment and various online APIs. Core features include fully automatic video translation, audio transcription to SRT subtitles with speaker diarization, multi-role AI dubbing, and zero-shot voice cloning via F5-TTS, CosyVoice, and GPT-SoVITS. It supports ASR models like Faster-Whisper, OpenAI Whisper, and Alibaba Qwen; LLM translation via DeepSeek, ChatGPT, Claude, Gemini, and Ollama; and TTS via Edge-TTS, OpenAI, Azure, and ChatTTS. Interactive editing allows manual proofreading at each stage. Deployment options include a pre-packaged Windows .exe, source deployment with uv on macOS/Linux/Windows, and Docker containerized deployment. It offers a GUI, a CLI for headless/batch processing, and a WebUI for remote access. Utility tools for vocal separation, video/subtitle merging, and audio-video alignment are included.