English

Transcribe Audio & Video to Text

Turn recordings, interviews, lectures and videos into text and subtitles with AI that runs on your device.

Choose an audio or video fileor drag it here · MP3, WAV, M4A, MP4, WEBM…
🔒 Your files never leave your device. Processing happens in your browser.

The first use downloads the speech model (about 80–250 MB depending on accuracy). Long files take a while on slower computers.

How to use it

  1. Choose an audio or video file.
  2. Pick the language (or let it detect) and the accuracy level.
  3. Wait for the transcript, then copy it or download it as text or SRT subtitles.

Questions and answers

Is this transcription really free?

Yes. It uses OpenAI's open-source Whisper speech model running inside your browser, so there are no per-minute fees.

Is my recording uploaded?

No. The speech model is downloaded to your device and the audio is processed locally.

How accurate is it?

Very good for clear speech. Choose 'Best' for accents, noisy audio or less common languages; it is slower and downloads a larger model.

More tools you might like