Desktop app that transcribes audio and video fully offline on your own device, using Whisper and other speech models.
tmoroney/auto-subs
Local-first AI subtitle generator that runs offline and plugs into DaVinci Resolve, Premiere Pro and After Effects.
Open-source alternative to:Descript
- Stars
- 4,409
- Forks
- 305
- Open issues
- 123
- Last commit
- 15 days ago
What is it?
AutoSubs turns audio or video into timestamped subtitles entirely on your own machine, with no cloud service or subscription required. It runs as a standalone desktop app on macOS, Windows and Linux, and can also be used from inside DaVinci Resolve or through a CEP extension for Adobe Premiere Pro and After Effects.
The app offers a choice of local speech recognition models, from small, lightweight Whisper variants to larger multilingual models, and supports speaker diarization so each speaker can be labeled and styled separately. Subtitles can be edited in the app and exported as SRT or plain text, or sent back to Resolve as styled subtitles.
The project is MIT-licensed. Some optional models, such as the MMS forced-alignment model used for word-level timestamps, are downloaded separately under their own noncommercial license.
Key features
- 01Generates timestamped subtitles from audio or video locally.
- 02Offers multiple model families, including Whisper, Parakeet and SenseVoice.
- 03Detects and labels individual speakers.
- 04Supports transcription and translation across many languages.
- 05Integrates with DaVinci Resolve, Premiere Pro and After Effects.
- 06Provides a command-line interface for scripted use.
Use cases
- Adding subtitles to video edits in DaVinci Resolve without uploading footage to a cloud service.
- Generating caption tracks for Premiere Pro projects from timeline audio.
- Transcribing interviews or podcasts with speaker labels for editing.
- Creating SRT files for videos in languages that specialist models cover.
Quick start
- 1
Install AutoSubs on macOS with Homebrew
brew install --cask auto-subs - 2
Download the installer for your platform from the releases page
- 3
Launch AutoSubs, select an audio or video file, then click Transcribe
Things to know
- The optional MMS forced-alignment model is licensed CC BY-NC 4.0, which is noncommercial only.
- The Mac App Store version of DaVinci Resolve is not supported by the Resolve integration.
Topics
FAQ
- What is auto-subs?
- Local-first AI subtitle generator that runs offline and plugs into DaVinci Resolve, Premiere Pro and After Effects. AutoSubs turns audio or video into timestamped subtitles entirely on your own machine, with no cloud service or subscription required. It runs as a standalone desktop app on macOS, Windows and Linux, and can also be used from inside DaVinci Resolve or through a CEP extension for Adobe Premiere Pro and After Effects.
- Is auto-subs free to use? What license does it have?
- auto-subs is open source under the MIT license. Check the license terms before using it in commercial products.
- Is auto-subs still maintained?
- Actively maintained. The last commit to auto-subs was on Oct 5, 2026.
- What can I use auto-subs for?
- Adding subtitles to video edits in DaVinci Resolve without uploading footage to a cloud service. Generating caption tracks for Premiere Pro projects from timeline audio. Transcribing interviews or podcasts with speaker labels for editing. Creating SRT files for videos in languages that specialist models cover.
- How do I install auto-subs?
- Install AutoSubs on macOS with Homebrew: brew install --cask auto-subs Download the installer for your platform from the releases page Launch AutoSubs, select an audio or video file, then click Transcribe
- Where can I get auto-subs?
- The source code and installation instructions are on GitHub: https://github.com/tmoroney/auto-subs
Summary generated by AI from the project's README. GitHub stats refresh daily.
Related projects
Open-source, local-first AI dictation app that turns speech into text on macOS and Windows, working offline with Whisper.
Desktop app that transcribes and translates audio and video offline on your computer, built on OpenAI's Whisper.
Privacy-first AI meeting assistant that records, transcribes and summarizes meetings locally on macOS and Windows, with optional Ollama or cloud LLM summaries.
Open-source local subtitling for any video: Whisper transcription, translation, styling and burn-in, in the browser, desktop app or CLI, without uploading the video.
C/C++ port of OpenAI's Whisper speech recognition model for fast, offline, dependency-free speech-to-text on CPU and GPU.