# tmoroney/auto-subs

On-device subtitle generation that connects directly to DaVinci Resolve, Premiere, and After Effects.

Repository: https://github.com/tmoroney/auto-subs
Canonical: https://ross.abutalabs.com/products/auto-subs
Homepage: https://tom-moroney.com/auto-subs/
Language: TypeScript
License: MIT
License Family: permissive
Topics: ai, davinci-resolve, subtitles, davinci, resolve, speech-to-text, transcribe, premiere, video-editing, cross-platform, rust, transcription
Last push: 2026-08-02T21:47:49+00:00

## Health v2 (maintenance only)
Score: 94/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 95, release rhythm 94, longevity 90
- inputs: {"age_days": 1268, "days_push": 31, "days_rel": 43, "gap_med": 2, "n_releases_24m": 26}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 4091, forks 266 (observed 2026-08-28T04:08:34.570722+00:00)

## What it is
AutoSubs is a local-first desktop application that generates AI subtitles on-device using Whisper, Moonshine, and Parakeet models, with speaker diarization and 100+ language support. It works standalone or connects directly to DaVinci Resolve, Adobe Premiere Pro, and After Effects to place styled subtitles on the editing timeline.

## Use cases
- generate subtitles for videos locally without cloud services
- add styled captions directly on a DaVinci Resolve timeline
- transcribe interviews with speaker labels in Premiere Pro
- translate subtitles into other languages
- export transcripts as SRT files
- create per-speaker styled subtitles for podcasts or YouTube videos

## When to choose
- you need on-device transcription with no data leaving your machine
- you edit in DaVinci Resolve, Premiere Pro, or After Effects and want timeline-integrated subtitles
- you need speaker diarization and per-speaker subtitle styling
- you want a free, open-source alternative to subscription captioning services

## When to avoid
- you need cloud-scale batch transcription of large media libraries
- you require subtitle formats or NLE integrations beyond SRT/text and the supported editors
- you need frame-accurate burned-in caption rendering rather than subtitle track generation

## Facets
- artifact type: application
- maturity: active
- function: speech-recognition, nlp, video-processing, gui
- domain: speech-processing, media, artificial-intelligence
- platform: windows, cross-platform
- tags: subtitles, transcription, davinci-resolve, premiere-pro, after-effects, whisper, speaker-diarization, local-first, video-editing, srt, video, macos, linux, desktop

## Member repositories
- tmoroney/auto-subs (main) score 94

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:34.570722+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 2026-08-29T18:23:21.288084+00:00, confidence not recorded.
  - readme: https://github.com/tmoroney/auto-subs (fetched 2026-08-28T04:08:34.570722+00:00, sha a74ad6a07370)
  - homepage: https://tom-moroney.com/auto-subs/ (fetched 2026-08-29T09:15:23.901986+00:00, sha e210fbdc8ecd)
- Data as of 2026-08-30T08:39:29.467469+00:00.