# x007xyz/flycut-caption

A complete video subtitle editing React component with AI-powered speech recognition and visual editing capabilities.

Repository: https://github.com/x007xyz/flycut-caption
Canonical: https://ross.abutalabs.com/products/flycut-caption
Homepage: https://caption.flycut.co
Language: TypeScript
License: NOASSERTION
License Family: other
Last push: 2026-07-10T06:25:44+00:00

## Health v2 (maintenance only)
Score: 78/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 91, release rhythm 92, longevity 24
- inputs: {"age_days": 345, "days_push": 54, "days_rel": 54, "gap_med": 0, "n_releases_24m": 2}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1753, forks 234 (observed 2026-08-28T04:05:31.882059+00:00)

## What it is
FlyCut Caption is an AI-powered video subtitle editing tool built as a React component and web/desktop app, offering speech recognition with Whisper (browser) and FunASR (desktop), bilingual dual-track editing, and smart silence cutting. It supports exporting SRT/JSON subtitles or hard-burning dual subtitles into exported video.

## Use cases
- generate subtitles for videos automatically with AI speech recognition
- edit bilingual dual-track subtitles with AI translation
- remove silent gaps from video recordings with one click
- burn subtitles directly into exported video files
- transcribe lectures and online courses into captions
- export SRT subtitle files from video or audio
- clean up talking-head videos by cutting pauses and mistakes

## When to choose
- you need an integrated subtitle generation, editing, and hard-burn export pipeline
- you want local/private AI transcription via Whisper or FunASR rather than cloud APIs
- you produce bilingual content needing primary and secondary subtitle tracks
- you want a reusable React subtitle editor component in your own app

## When to avoid
- you only need simple manual subtitle editing without AI transcription
- you require a full professional non-linear video editor
- you need server-side batch transcription at scale rather than browser/desktop processing
- your project cannot accept the project's non-standard license

## Facets
- artifact type: application
- maturity: active
- function: speech-recognition, video-processing, nlp, ui-components, machine-learning
- domain: speech-processing, media, developer-tools
- platform: cross-platform, browser
- tags: subtitles, whisper, funasr, tauri, react, bilingual, video-editing, srt, hard-burn, ai-translation, video, natural-language-processing, web-server, desktop, nodejs

## Member repositories
- x007xyz/flycut-caption (main) score 78

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:31.882059+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 2026-08-30T03:28:15.929515+00:00, confidence not recorded.
  - readme: https://github.com/x007xyz/flycut-caption (fetched 2026-08-28T04:05:31.882059+00:00, sha dfff5f07282b)
  - homepage: https://caption.flycut.co (fetched 2026-08-29T11:06:41.051284+00:00, sha f92b60d51709)
  - site_page: https://caption.flycut.co/en/features (fetched 2026-08-29T11:06:41.060378+00:00, sha 1b3437fe2e91)
- Data as of 2026-08-30T08:39:29.467469+00:00.