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.

GitHub stars: 910
last updated: May 19, 2026

View on GitHub

Install

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

Installs into .claude/skills of the current project.

Files

Violin — operating skill

Always uses the default config (Together for translation, cartesia/sonic-3 for TTS). If the user asks for OpenAI, ElevenLabs, or custom configs, stop and point them to the Violin repo — those flows aren't supported through the global CLI.

Pre-flight

Run these silently first. Abort if any fails:

command -v violin                 # 1. CLI on PATH
test -f "<input>"                 # 2. Input exists
printenv TOGETHER_API_KEY         # 3. Key available

If violin is missing: tell the user to uv tool install violin, then violin --install-skill to refresh this skill file. Do not auto-install.

If TOGETHER_API_KEY is missing: