# WEIFENG2333/VideoCaptioner

🎬 卡卡字幕助手 | VideoCaptioner - 基于 LLM 的智能字幕助手 - 视频字幕生成、断句、校正、字幕翻译全流程处理！- A powered tool for easy and efficient video subtitling.

Repository: https://github.com/WEIFENG2333/VideoCaptioner
Canonical: https://ross.abutalabs.com/products/videocaptioner
Homepage: https://www.videocaptioner.cn
Language: Python
License: GPL-3.0
License Family: copyleft
Topics: ai, subtitle, translate, video-subtile
Last push: 2026-07-19T18:30:44+00:00

## Health v2 (maintenance only)
Score: 82/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 93, release rhythm 89, longevity 47
- inputs: {"age_days": 671, "days_push": 45, "days_rel": 77, "gap_med": 17.0, "n_releases_24m": 11}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 15764, forks 1356 (observed 2026-08-28T04:11:13.990166+00:00)

## What it is
VideoCaptioner is an open-source AI-powered video subtitling tool that handles the full pipeline: speech recognition, LLM-based subtitle segmentation and correction, translation, and burning subtitles into video. It ships as both a desktop GUI and a CLI, with free built-in ASR and translation options plus optional LLM API integration.

## Use cases
- generate subtitles for a video automatically
- translate srt subtitles to another language
- fix and re-segment auto-generated subtitles with an LLM
- burn subtitles into a video file
- transcribe video audio to text for free
- add translated captions to videos for international audiences
- download a YouTube video and caption it

## When to choose
- you want an end-to-end subtitle workflow without stitching multiple tools
- you need a free, offline-capable option (Bijian ASR, Bing/Google translation)
- you prefer both a GUI desktop app and scriptable CLI
- you want LLM-polished subtitles with terminology correction at low cost

## When to avoid
- you need real-time live captioning
- you require only manual subtitle editing without AI features
- you need permissive licensing for proprietary redistribution (GPL-3.0)
- you need enterprise-grade batch processing pipelines

## Facets
- artifact type: application
- maturity: active
- function: speech-recognition, nlp, llm-inference, video-processing, cli, gui, internationalization
- domain: media, artificial-intelligence, developer-tools
- platform: windows, python, cross-platform
- tags: subtitles, asr, whisper, captioning, subtitle-translation, srt, llm, video-subtitling, video, natural-language-processing, macos, linux, docker

## Member repositories
- WEIFENG2333/VideoCaptioner (main) score 82

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:13.990166+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 2026-08-29T17:05:33.250191+00:00, confidence not recorded.
  - readme: https://github.com/WEIFENG2333/VideoCaptioner (fetched 2026-08-28T04:11:13.990166+00:00, sha c6d7d9e10bb8)
  - homepage: https://www.videocaptioner.cn (fetched 2026-08-29T08:03:25.233601+00:00, sha 146de934c7bf)
  - site_page: https://www.videocaptioner.cn/guide/getting-started (fetched 2026-08-29T08:03:25.242811+00:00, sha 3d63acc99fa4)
  - site_page: https://www.videocaptioner.cn/guide/faq (fetched 2026-08-29T08:03:25.244952+00:00, sha ee0be331d33f)
  - registry_pypi: https://pypi.org/pypi/videocaptioner/json (fetched 2026-08-29T08:03:25.246606+00:00, sha 219c31701e44)
- Data as of 2026-08-30T08:39:29.467469+00:00.