# jianchang512/pyvideotrans

Translate the video from one language to another and embed dubbing & subtitles.

Repository: https://github.com/jianchang512/pyvideotrans
Canonical: https://ross.abutalabs.com/products/pyvideotrans
Homepage: https://pyvideotrans.com
Language: Python
License: GPL-3.0
License Family: copyleft
Topics: text-to-speech, video-transition, speech-to-text
Last push: 2026-08-26T05:46:33+00:00

## Health v2 (maintenance only)
Score: 90/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 99, release rhythm 87, longevity 76
- inputs: {"age_days": 1066, "days_push": 7, "days_rel": 10, "gap_med": 7.0, "n_releases_24m": 61}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 18812, forks 2326 (observed 2026-08-28T04:11:27.152080+00:00)

## What it is
pyVideoTrans is an open-source desktop application (with WebUI and CLI modes) that translates videos from one language to another. It provides a full pipeline of speech recognition, subtitle translation, AI dubbing with multi-role voices and voice cloning, and video synthesis, supporting 30+ local and online model APIs.

## Use cases
- translate a video from Chinese to English with dubbed audio
- generate SRT subtitles from audio or video files
- add AI dubbing with different voices per speaker
- clone a voice for zero-shot dubbing
- batch transcribe audio recordings to text
- translate existing subtitle files
- separate vocals from background audio in a video
- run headless video translation on a server via CLI

## When to choose
- you need an end-to-end video translation and dubbing workflow in one tool
- you want to mix local offline models (Faster-Whisper, Ollama, F5-TTS) with online APIs
- you need batch subtitle generation or SRT translation
- you want a free, unrestricted GPL tool with GUI, WebUI, and CLI interfaces

## When to avoid
- you only need simple subtitle editing without translation or dubbing
- you require a lightweight library to embed in your own code rather than a standalone application
- you cannot accept GPL-3.0 licensing constraints
- you need real-time live translation of streams

## Facets
- artifact type: application
- maturity: active
- function: speech-recognition, tts, video-processing, nlp, audio-processing, cli, gui
- domain: media, artificial-intelligence
- platform: windows, cross-platform, python
- tags: video-translation, dubbing, subtitles, voice-cloning, asr, srt, whisper, webui, video, audio, natural-language-processing, localization, macos, linux, docker, web-server

## Member repositories
- jianchang512/pyvideotrans (main) score 90

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:27.152080+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 2026-08-29T17:01:17.342981+00:00, confidence not recorded.
  - readme: https://github.com/jianchang512/pyvideotrans (fetched 2026-08-28T04:11:27.152080+00:00, sha 9fe27029ea49)
  - homepage: https://pyvideotrans.com (fetched 2026-08-29T07:59:11.778067+00:00, sha ea83000fc034)
- Data as of 2026-08-30T08:39:29.467469+00:00.