Video Translator

Translates and dubs videos into 33 languages using Together AI for transcription and Cartesia Sonic for speech synthesis. It handles the full pipeline: extracts audio, transcribes with Whisper, translates the text, generates dubbed speech, and burns subtitles back in. Sixteen languages get native speaker voices; the rest fall back to multilingual English voices that work but aren't quite native. The CLI defaults to voiceover mode, mixing dubbed audio over a quieted original, which feels more natural than a full replacement. Installs via uv tool as `violin`. One thing to know upfront: it always runs the complete pipeline even if you only want subtitles, so check costs first on longer videos.

Install to Claude Code

npx -y skills add shang-zhu/violin --skill video-translator --agent claude-code