Brothers, this is great! Get it installed right away! Kevin Lin, postdoctoral fellow at Oxford, former researcher at Meta and Microsoft, just released Violin, an open-source video translation skill.

Video is already the absolute mainstream form of content on the internet. Yet most high-quality lectures, talks, and podcasts are locked behind a single language, completely inaccessible to a global audience. Violin seamlessly strings together ASR, LLM translation, and TTS into a pipeline.

“Input a video, and it automatically performs speech recognition, multi-language translation, and natural voice synthesis.”

The two most useful features: you can personalize the translation style, turning an academic report into a version even a child can understand; and you can chat directly with the video, with answers based on the video content for any question. It supports Web app, CLI, and Agent Skill, all MIT open-source.

From now on, high-quality content no longer belongs to just one language — it truly goes global. Demo, blog, and GitHub are all in the original post. If you’re working in content, education, cross-language communication, or developing multimodal agents, this Skill is worth trying immediately.

What do you think AI should solve next: content creation, or content globalization?

Project URL: https://github.com/shang-zhu/violin…

shang-zhu/violin

Source: https://github.com/shang-zhu/violin

🎻 Violin

Open-source Video Translation Skill.

🌐 Live demo (https://www.violin-ai.com) · 📝 Blog post (https://www.together.ai/blog/violin-open-source-translation-skill) · 📜 MIT License (https://github.com/shang-zhu/violin/blob/main/LICENSE)

Upload a video. Violin transcribes the speech, translates it, synthesizes a native-sounding voice-over in the target language, and remuxes it back into the video — fully aligned, with optional SRT subtitles. Available as a CLI, a FastAPI web app, and a Claude Code skill.

✨ Features

• 33 target languages with handpicked native-speaker voices for the 16 most-used ones (Cartesia Sonic 3 + ElevenLabs)
• In-video Q&A — ask questions about any moment in the dubbed video; answers use nearby subtitles plus sampled frames
• Natural-language voice picker — describe the voice you want, an LLM picks from the catalog
• 6 style profiles (experimental) — standard / kids / academic / casual / storyteller / news
• Pluggable stack — Together / OpenAI / ElevenLabs interchangeable for every stage, one YAML

🚀 Quick start

Try it without installing anything

The live demo runs at https://www.violin-ai.com — drop a short clip in, get a dubbed video out in a few minutes.

Run locally

Requires Python 3.10+ and ffmpeg on PATH.

curl -LsSf https://astral.sh/uv/install.sh | sh # install uv if you don't have it
uv tool install violin # recommended — faster, isolated
# or: pip install violin # if you'd rather install into your current Python env
export TOGETHER_API_KEY=... # get one at https://api.together.ai (add to ~/.zshrc to persist)

Three ways to use it:

1. CLI — translate one file:

violin lecture.mp4 lecture_zh.mp4 --language Chinese

2. Web app — full REST API + browser UI:

violin-api
# → http://127.0.0.1:8000 (browser UI)
# → http://127.0.0.1:8000/docs (interactive API docs)

3. Claude Code skill — invoke from any Claude Code session:

violin --install-skill # one-time: copies the skill into ~/.claude/skills/
claude
> please use the violin skill to translate path/to/video.mp4 into Chinese

Run from source (for hacking on the pipeline)

git clone https://github.com/shang-zhu/violin.git
cd violin
uv sync
cp .env.example .env # then fill in TOGETHER_API_KEY
uv run main.py lecture.mp4 lecture_zh.mp4 --language Chinese

To use the violin / violin-api commands globally while edits to your local source reflect immediately, install editable:

uv tool uninstall violin # if you've installed the PyPI version
uv tool install --editable .

After this, violin / violin-api run from your local checkout — edit any file and the next invocation picks it up; no rebuild needed. To switch back to PyPI: uv tool uninstall violin && uv tool install violin.

🎬 How Violin works

Video
│
├─ ffmpeg ─────────────────────► Extract audio (16 kHz WAV)
│
├─ Whisper Large v3 ────────────► Word-level timestamps → sentence segments
│
├─ LLM (DeepSeek V4 Pro by default) ──► Translate each segment, respecting style profile
│
├─ TTS (Cartesia Sonic 3 by default) ─► Synthesize dubbed audio per segment
│
└─ ffmpeg ─────────────────────► Speed-align video to dubbed audio, concat with freeze-frame fallback,
                                 single-pass AAC encode the audio track, write output mp4 + optional SRT

⚙️ Configuration

Override any default by writing your own YAML and passing it with --config my.yaml — only the keys you want to change need to appear; values deep-merge with the built-in defaults (https://github.com/shang-zhu/violin/blob/main/config/default.yaml).

Switch providers

# config/default.yaml — pick the stack you want
models:
  transcription:
    provider: together   # together | openai
    model: openai/whisper-large-v3   # together → openai/whisper-large-v3 | openai → whisper-1
  translation:
    provider: together   # together | openai
    model: deepseek-ai/DeepSeek-V4-Pro  # together → deepseek-ai/DeepSeek-V4-Pro | openai → gpt-5.5
  tts:
    provider: together   # together | elevenlabs | openai
    model: cartesia/sonic-3  # together → cartesia/sonic-3 | elevenlabs → eleven_v3 | openai → tts-1-hd

Production overrides

A starter config/prod.yaml is included for public deployments. It adds upload limits, serializes jobs, and caps ffmpeg concurrency. The included Dockerfile + docker-compose.yml + Caddyfile are how the live demo is hosted — docker compose up -d --build after filling .env is enough to put a copy of Violin behind auto-HTTPS on any Docker host.

Environment variables

You only need keys for the providers you actually pick. Pure-OpenAI deployments (all stages on openai) work too — OPENAI_API_KEY alone is enough. Same idea for ElevenLabs.

🎭 Style profiles

Six built-in profiles tune both the translation LLM prompt and the TTS delivery. Use --style <name> on the CLI or pass style in API requests.

Add your own by editing prompts/styles.yaml. See all available styles: violin --style list.

💻 CLI usage

Examples use the PyPI-installed violin command. If you’re running from a git checkout, substitute uv run main.py for violin (and uv run run_api.py for violin-api).

# Basic
violin lecture.mp4 lecture_es.mp4 --language Spanish

# Pick a style
violin talk.mp4 talk_zh.mp4 --language Chinese --style kids

# Pick a specific voice
violin lecture.mp4 lecture_fr.mp4 --language French --voice "french narrator man"

# Skip SRT
violin lecture.mp4 lecture_ja.mp4 --language Japanese --no-subtitles

# Full replacement (no original audio underneath)
violin lecture.mp4 lecture_ko.mp4 --language Korean --no-voiceover

# Custom config (e.g. switch to OpenAI/ElevenLabs)
violin lecture.mp4 lecture_it.mp4 --language Italian --config config/other_api.yaml

CLI flags

🛰️ Web app & REST API

violin-api                              # default dev mode
violin-api --host 0.0.0.0 --port 8080   # bind everywhere
violin-api --config config/prod.yaml    # production overrides (requires a git checkout for config/prod.yaml)

Core flow: POST /jobs to start, GET /jobs/{id} to poll, GET /jobs/{id}/video and /srt to download, POST /jobs/{id}/chat for in-video Q&A. Full list with request/response schemas at /docs.

Example

# Submit
JOB=$(curl -s -X POST http://localhost:8000/jobs \
  -F "[email protected]" \
  -F "language=Spanish" \
  -F "style=academic" | jq -r .id)

# Poll
curl -s http://localhost:8000/jobs/$JOB | jq '{status, progress}'

# Download
curl -OJ http://localhost:8000/jobs/$JOB/video
curl -OJ http://localhost:8000/jobs/$JOB/srt

Job data lives under jobs/{id}/. Set api.job_ttl_hours to auto-delete jobs older than N hours (default 0 = disabled; config/prod.yaml uses 24h for the public demo).

🌍 Supported languages

Violin supports 33 target languages. The 16 below ship with handpicked native-speaker voices for each provider; the rest fall back to the English voice catalog (which is multilingual under both Cartesia Sonic 3 and ElevenLabs eleven_v3). Ordered by native-speaker population.

The 17 fallback languages (using the English voice catalog), also ordered by native speakers: Vietnamese, Tamil, Indonesian, Malay, Ukrainian, Romanian, Thai, Greek, Hungarian, Catalan, Czech, Bulgarian, Danish, Slovak, Croatian, Finnish, Norwegian.

🤝 Contributing

PRs welcome. Got questions or hit a bug? Email [email protected] or open an issue.

⚠️ Disclaimer

This is a personal open-source project, not a Together AI product. Users are responsible for ensuring they have the right to download and translate any content they process. Designed for Creative Commons, public domain, your own recordings, and other content you have permission to use.

📜 License

MIT (https://github.com/shang-zhu/violin/blob/main/LICENSE) — use it freely, including commercially.

🙏 Acknowledgements

Built on top of Together AI (https://together.ai), Whisper (https://github.com/openai/whisper), Cartesia Sonic 3 (https://cartesia.ai), ElevenLabs (https://elevenlabs.io), FastAPI (https://fastapi.tiangolo.com/), and ffmpeg (https://ffmpeg.org).