# shang-zhu/violin

Open-source Video Translation Skill

Repository: https://github.com/shang-zhu/violin
Canonical: https://ross.abutalabs.com/products/violin
Homepage: https://www.violin-ai.com/
Language: Python
License: MIT
License Family: permissive
Topics: agent-skills, asr, dubbing, video-translation
Last push: 2026-05-19T01:51:24+00:00

## Health v2 (maintenance only)
Score: 52/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 83, release rhythm 35, longevity 10
- inputs: {"age_days": 148, "days_push": 107, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1047, forks 156 (observed 2026-08-28T04:03:21.898903+00:00)

## What it is
Violin is an open-source video translation tool that transcribes speech, translates it into 33 languages, synthesizes a native-sounding voice-over, and remuxes it back into the video with synced SRT subtitles. It is available as a CLI, a FastAPI web app, and a Claude Code skill, with a pluggable stack of AI providers (Together, OpenAI, ElevenLabs).

## Use cases
- translate a video into another language with dubbed voice-over
- generate synced subtitles for a video in a foreign language
- dub a lecture into Chinese or other languages
- add natural-sounding voice-over to videos using TTS
- transcribe speech from a video with ASR
- translate videos from the command line
- run a self-hosted video translation web app
- translate videos from within Claude Code

## When to choose
- you need to dub videos into many languages with native-sounding voices
- you want a scriptable CLI or self-hosted API for video translation
- you want pluggable ASR/translation/TTS providers configured via YAML
- you want subtitles generated alongside the dubbed audio

## When to avoid
- you need real-time live translation or streaming dubbing
- you need frame-perfect lip-sync or visual dubbing effects
- you want a fully free pipeline with no paid API keys for TTS or LLMs
- you need offline translation without cloud AI services

## Facets
- artifact type: cli-tool
- maturity: active
- function: speech-recognition, tts, video-processing, nlp, llm-inference, cli, api-framework
- domain: speech-processing, artificial-intelligence, media
- platform: python, cli, cross-platform
- tags: video-translation, dubbing, subtitles, asr, agent-skills, claude-code-skill, elevenlabs, together-ai, whisper, fastapi, video, natural-language-processing, localization, web-server

## Member repositories
- shang-zhu/violin (main) score 52

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:21.898903+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T07:01:09.672905+00:00, confidence not recorded.
  - readme: https://github.com/shang-zhu/violin (fetched 2026-08-28T04:03:21.898903+00:00, sha 948fc98dc8b2)
  - homepage: https://www.violin-ai.com/ (fetched 2026-08-29T13:02:53.867636+00:00, sha cccc54d73e88)
  - registry_pypi: https://pypi.org/pypi/violin/json (fetched 2026-08-29T13:02:53.876894+00:00, sha d39209fb251d)
- Data as of 2026-08-30T08:39:29.467469+00:00.