# Huanshere/VideoLingo

Netflix-level subtitle cutting, translation, alignment, and even dubbing - one-click fully automated AI video subtitle team | Netflix级字幕切割、翻译、对齐、甚至加上配音，一键全自动视频搬运AI字幕组

Repository: https://github.com/Huanshere/VideoLingo
Canonical: https://ross.abutalabs.com/products/videolingo
Homepage: https://docs.videolingo.io
Language: Python
License: Apache-2.0
License Family: permissive
Topics: ai-translation, dubbing, localization, video-translation, voice-cloning
Last push: 2026-08-23T15:23:27+00:00

## Health v2 (maintenance only)
Score: 80/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 72, longevity 53
- inputs: {"age_days": 754, "days_push": 10, "days_rel": 186, "gap_med": 1.0, "n_releases_24m": 43}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 18266, forks 2013 (observed 2026-08-28T04:11:26.512151+00:00)

## What it is
VideoLingo is an all-in-one AI video translation, localization, and dubbing tool that produces Netflix-quality single-line subtitles with word-level alignment via WhisperX. It automates the full pipeline from YouTube download through NLP/LLM-based subtitle segmentation, multi-step translation, and cloned-voice dubbing via GPT-SoVITS, Azure, OpenAI, and other TTS providers.

## Use cases
- translate youtube videos into another language with subtitles
- add ai-generated dubbing with cloned voice to videos
- generate netflix-style single-line subtitles automatically
- localize video content for international audiences
- transcribe and align subtitles word-by-word
- batch translate video content for social media reposting

## When to choose
- you want a one-click, end-to-end video translation and dubbing pipeline
- you need high-quality single-line subtitles that meet Netflix standards
- you want voice cloning dubbing with GPT-SoVITS or multiple TTS options
- you prefer a Streamlit UI with resumable, logged processing steps

## When to avoid
- you need real-time or live-stream translation
- you want fully offline processing without any LLM API (though Ollama/Edge TTS is possible with reduced quality)
- you need multi-line or stylized subtitle formats
- you lack a GPU or API budget and need top-tier transcription/dubbing quality

## Facets
- artifact type: application
- maturity: active
- function: speech-recognition, tts, nlp, machine-learning, video-processing, internationalization, llm-inference, gui
- domain: media, artificial-intelligence
- platform: windows, python, self-hosted
- tags: subtitle-translation, dubbing, voice-cloning, whisperx, yt-dlp, streamlit, netflix-style-subtitles, video-localization, video, localization, natural-language-processing, automation, macos, linux, docker, gpu

## Member repositories
- Huanshere/VideoLingo (main) score 80

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:26.512151+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 2026-08-29T17:02:05.786749+00:00, confidence not recorded.
  - readme: https://github.com/Huanshere/VideoLingo (fetched 2026-08-28T04:11:26.512151+00:00, sha 4781f29b0850)
  - homepage: https://docs.videolingo.io (fetched 2026-08-29T07:59:54.194375+00:00, sha ccd1dbb0934a)
  - site_page: https://docs.videolingo.io/docs/introduction (fetched 2026-08-29T07:59:54.203391+00:00, sha c5abcc28c4c7)
  - site_page: https://docs.videolingo.io/docs/start (fetched 2026-08-29T07:59:54.205556+00:00, sha 753c3088c8bb)
- Data as of 2026-08-30T08:39:29.467469+00:00.