Recording inputLocal Whisper studio
Drop your audio or video hereOr choose a recording to get started.
No recording selected

Tiny transcription · 40.8 MB CPU / 119.7 MB GPU weights. Runtime files download too.

Choose a file or record your microphone.

Download and processing settings

Model weights: 40.8 MB for WebAssembly; 119.7 MB for GPU. Configuration, tokenizer and runtime files add a smaller download. Source: Hugging Face file sizes, checked 2026-10-30.

Model file sizes and source · Last checked October 30, 2026

Tiny uses the least memory. Base and Small may improve recognition but need more memory and time. Try a short sample first. No accuracy or speed is guaranteed.

Audio is processed locally. Model files download from Hugging Face when you start, then stay in your browser cache when storage permits. How privacy works

Saved on this device

Recordings and edits are stored in this browser when local storage is available. Export an important transcript before clearing browser data. The delete control clears app storage and its model cache. Use browser cache controls to remove any browser-managed download copies too.

Example export / SRTFrom the licensed speech example ↗
1
00:00:00,520 --> 00:00:04,180
I mentioned to the universe, sir, I exist.

Generate, listen, correct

Choose the spoken language, start transcription and review the draft. The export selector includes SRT and VTT. A model transcript does not reliably identify speakers or describe meaningful sounds. Add that information yourself when preparing accessibility captions.

These are separate subtitle files. The tool does not burn text into video. Test the export with the exact final video, especially after cutting or adding an intro.

Sources

  1. Whisper paper, appendix tables and normalization method · OpenAI / Radford et al. · Checked 2026-10-30
  2. YouTube subtitle import formats · Google / YouTube · Checked 2026-10-30