Audio
Audio

Speech to Text Transcriber

Turn a recording into text with time stamps. It runs in your browser, so the sound never leaves your device.

Private by design

Your inputs stay on your device and are not sent to our servers. Optional usage analytics does not receive your files or tool inputs.

Preparing tool

How to use Speech to Text Transcriber

  1. Choose an audio or video file, or try the sample.
  2. Press Start. The first time, the speech model downloads (about 41 MB) and is kept by your browser.
  3. Fix any words, click a time to hear it, then download TXT, SRT or VTT.
Read the detailed guide →

What are the limits of Speech to Text Transcriber?

English only (the small English Whisper model). Accuracy drops with noise, strong accents and several people talking at once, and there is no speaker labelling. Time stamps are about one second accurate. It runs on your device, so long files are slow on phones; keep files under 60 minutes. Nothing is uploaded.

YOUR BROWSER, YOUR CHOICE