Anysub turns audio and video into subtitles with an easy-to-use web UI. Everything runs on your own machine.
It is the successor to Whishper, rewritten from scratch.
Features
- Transcription with Whisper, from the
tinymodel tolarge-v3-turbo. - Word-level timings.
- A subtitle editor with a waveform timeline, undo and autosave.
- Warnings for subtitles that are too fast, too long, or overlap.
- Export to SRT, WebVTT, plain text or JSON.
- Uploads that resume, for hours-long files.
- A searchable library.
- Admin pages for models, defaults, upload limits, disk space and workers.
Install
On a Linux x86-64 host with Docker and Docker Compose:
mkdir anysub && cd anysub
curl -fsSLO https://github.com/pluja/anysub/releases/latest/download/compose.yaml
docker compose up -d
Open http://localhost:5173 and create your account. It asks for a setup code, which you find with docker compose logs web.
Install covers requirements, Podman, NVIDIA GPUs, reverse proxies and building from source.
Coming from Whishper 3
Whishper 3 is no longer maintained, and Anysub can't read its data. Coming from Whishper 3 explains how to move over. The old code is in the v3-legacy branch.
Not built yet
- Translation.
- Speaker labels.
- Watched folders.
- Import from a URL or an existing subtitle file.
- More than one account.
- Workers on other machines.
- ARM images.
These will come in 4.x releases. See the changelog.
Documentation
See docs.
AI disclosure
Large language models helped write the code and docs. A human reviews and tests every change before it ships.
