# chenyme/Chenyme-AAVT

这是一个全自动（音频）视频翻译项目。利用Whisper识别声音，AI大模型翻译字幕，最后合并字幕视频，生成翻译后的视频。

Repository: https://github.com/chenyme/Chenyme-AAVT
Canonical: https://ross.abutalabs.com/products/chenyme-aavt
Language: Python
License: MIT
License Family: permissive
Topics: faster-whisper, gpt-4, speech-recognition, video-translation, whisper, gpt-4o
Archived: true
Last push: 2025-04-07T05:48:22+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 15, release rhythm 8, longevity 70
- inputs: {"age_days": 989, "days_push": 513, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: archived
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3128, forks 248 (observed 2026-08-28T04:07:44.571003+00:00)

## What it is
Chenyme-AAVT is a fully automated audio/video translation application that uses Whisper (faster-whisper) for speech recognition, large language models like GPT-4, Claude, Gemini, and DeepSeek for subtitle translation, and merges the translated subtitles back into the video. It also supports standalone subtitle translation, AI-generated blog/marketing content, and voice simulation, with fully local and free deployment options.

## Use cases
- translate a video into another language automatically
- generate subtitles from audio or video with whisper
- translate srt subtitle files using an llm
- dub or re-voice translated videos
- auto-generate blog articles from video content
- batch transcribe and translate lectures or talks
- self-host a free video translation pipeline

## When to choose
- you want an end-to-end automated video translation workflow with minimal manual steps
- you need local/free deployment without paid transcription services
- you want flexible choice of LLM translation engines (ChatGPT, Claude, Gemini, DeepSeek, local models)
- you need subtitle editing, preview, and styling before final video output

## When to avoid
- you need real-time live speech translation (still on the roadmap)
- you require professional-grade human-quality dubbing or lip-sync correction
- you only need simple transcription without translation
- you need a lightweight CLI-only tool rather than a web application

## Facets
- artifact type: application
- maturity: active
- function: speech-recognition, nlp, video-processing, llm-inference, tts
- domain: artificial-intelligence, media
- platform: python, cross-platform, self-hosted
- tags: video-translation, subtitle-generation, whisper, faster-whisper, gpt-4, subtitle-translation, audio-transcription, ffmpeg, natural-language-processing, video, docker, web-server

## Member repositories
- chenyme/Chenyme-AAVT (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:44.571003+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 2026-08-30T07:26:18.886533+00:00, confidence not recorded.
  - readme: https://github.com/chenyme/Chenyme-AAVT (fetched 2026-08-28T04:07:44.571003+00:00, sha f7c78f143039)
- Data as of 2026-08-30T08:39:29.467469+00:00.