Transcribe audio and video
Drop an audio or video file here, or click to choose one
The first run downloads about 82MB for the AI model (cached afterwards)
How to use
- Load an audio or video file.
- Choose the accuracy and language, then press Transcribe.
- Fix the text while playing it back, then export SRT, VTT, or plain text.
FAQ
Is it free?
Yes. Every feature is free with no usage limits, and no account is needed.
Is my audio uploaded to a server?
No. The AI model is downloaded into your browser and runs on your own device — your audio and video never leave it.
How long does it take?
Roughly a quarter of the audio length with the standard model (about 2-3 minutes for 10 minutes of audio). The first run also downloads a few dozen megabytes for the model.
Which file formats are supported?
Audio such as MP3, WAV, M4A, and OGG, plus video such as MP4 and WebM — anything your browser can play.