Violin skill
A skill and CLI for translating and dubbing video: transcription, translation, voice synthesis and subtitles
- 1,089 ★ on the repository
- Last commit
- MIT
Extended access
Why this level
- Sends audio and text to external services with keys
- Runs video processing and writes files to disk
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/violinDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- Sends audio and text to external services with keys
- Runs video processing and writes files to disk
This is third-party code. Review the repository files before installing.
What it does
Violin translates a video into another language and produces subtitles. It transcribes the speech, translates it, synthesizes a voice-over in the target language and remuxes the track back into the video with aligned timing, optionally with SRT subtitles. It handles mp4, mkv and webm files, supports dozens of languages and can pick a voice from a description. It installs as the violin CLI (and a violin-api server), with a Claude Code skill on top that drives the CLI. Translation and synthesis models plug in through a YAML config: Together, OpenAI, ElevenLabs and others.
Who it is for. For content creators and localizers who need to translate and dub video.
Good fit when
- You need to translate and dub a video into another language
- You need timing-aligned subtitles for a video
- You want to localize a clip through an agent that drives the CLI
Not a fit when
- You have no keys for the translation and speech synthesis services
- You only need text translation without video work
Example request
Translate and dub this video into English and generate subtitlesLimitations
It needs keys for external services, by default Together for translation and Cartesia for synthesis, and some models are paid. Installation and running require Python and ffmpeg. The skill via the global CLI uses the default config; for OpenAI, ElevenLabs or custom settings you run the project directly. Access to some services from Russia without VPN is not guaranteed.
How to disable. Remove the video-translator skill from ~/.claude/skills and uninstall the CLI with uv tool uninstall violin.
FAQ
Which models are supported?
The stack is swappable via YAML: Together, OpenAI, ElevenLabs and others for translation and synthesis. The skill via the global CLI uses the default stack.
Are keys required?
Yes, translation and speech synthesis need keys for external services.
Discussion
No questions or reviews yet.
Related
SkillsA skill that teaches the agent to build narrated videos through narrator-ai-cli: source, template, music, voice, script and composing
A Codex and Claude Code skill: subtitles and a summary from a Douyin, Xiaohongshu, Bilibili or YouTube link or a local file
A skill that takes Claude Code from a song and lyrics to a finished Vocaloid-style lyric video, rendered in a browser.
A skill that turns a Bilibili, Douyin or YouTube video link into timestamped notes through local transcription
VideoCaptioner transcribes speech, translates subtitles and burns them into video with a single command from Claude Code.
Claude Real Video
claude-real-video
A skill that lets Claude watch a video: it pulls scene-aware, deduplicated frames and a speech transcript through whisper from a link or file
README in short
The README presents Violin as an open-source video translation tool available as a CLI, a FastAPI web app and a Claude Code skill. It transcribes speech, translates, synthesizes a voice-over and remuxes the track back with alignment, optionally with subtitles. It supports dozens of languages, voice picking by description and a swappable model stack via YAML. Installation is via uv or pip, and the skill is copied with violin --install-skill. MIT licensed.
README badge
Original SKILL.md
--- name: video-translator description: Dub a video into another language and generate subtitles using the default Together + Cartesia stack. Trigger when the user wants to translate / dub / voice-over a video file, or generate subtitles for it. Handles `.mp4` / `.mkv` / `.webm`. Installs as the `violin` CLI (and `violin-api` for the FastAPI server) via `uv tool install`. For alternative models (OpenAI / ElevenLabs) or custom configs, point the user to the repo. allowed-tools: Bash, Read --- # Violin — operating skill Always uses the default config (Together for translation, `cartesia/sonic-3` for TTS).