pyvideotrans

Why we included this project

pyVideoTrans is a practical pick for teams that localize video for international audiences. It takes a source video, transcribes the speech, translates the subtitles, generates dubbed audio, and re-synthesizes the final file in the target language, and you can pause at each stage to proofread the recognition, translation, and dubbing before the final render. The tool runs fully offline with local models like Faster-Whisper and Ollama, or against mainstream cloud APIs, and you can drive it from a GUI, a headless CLI for batch jobs, or a browser-based WebUI for server deployment. Multi-role dubbing and voice cloning keep different speakers sounding distinct in the dubbed version, which matters for interviews, courses, and documentaries. For anyone shipping translated video regularly, this removes most of the manual stitching between separate ASR, translation, and TTS tools.