whishper
Transcribe any audio to text, translate and edit subtitles 100% locally with a web UI. Powered by whisper models!
What is whishper?
Transcribe any audio to text, translate and edit subtitles 100% locally with a web UI. Powered by whisper models!
Overview of whishper
What it is
Anysub (formerly Whishper) is a web application that transcribes audio and video files into text using OpenAI's Whisper models. It runs entirely on the user's own computer or server, with no data sent to external services unless the user configures an external provider. The application includes a built-in subtitle editor for correcting text and timing, and supports export to common subtitle formats.
Key features
- Transcription using Whisper models from
tinytolarge-v3-turbo. - Word-level timing for subtitles.
- Subtitle editor with waveform timeline, undo, and autosave.
- Warnings for subtitles that are too fast, too long, or overlap.
- Export to SRT, WebVTT, plain text, or JSON.
- Resumable uploads for long files.
- Searchable library and admin pages for models, defaults, upload limits, disk space, and workers.
Use cases
- Creating subtitles for videos or audio recordings.
- Editing and correcting automatically generated subtitles.
- Running a private transcription service on local hardware.
Getting started
You need Linux on x86-64 with Docker and Docker Compose.1. Create a folder and download the Compose file:shmkdir anysub && cd anysubcurl -fsSLO https://github.com/pluja/anysub/releases/latest/download/compose.yaml2. Optional: download additional files for GPU or external providers (see repository README).3. Start Anysub:shdocker compose up -d4. Open http://localhost:5173 and create your account. The setup code is shown by docker compose logs web.
License and pricing
License: AGPL-3.0-only. The software is open source and free to use.
Based on the project's public README and repository metadata.