Transcribe audio to text
Speech to editable, timestamped text in 99 languages.
- 01Add audio
- 02Transcribe
- 03Export
Ready. Free
01 — Steps
How to transcribe audio to text
- Add audio
Drop an MP3, M4A, WAV or other recording, or record one with your microphone.
- Transcribe
Pick the language or let it be detected. The first run downloads the speech model once.
- Edit and export
Fix any word, click a timestamp to hear it, then copy or save TXT, SRT or VTT.
02 — Questions
Frequently asked questions
How accurate is it?
Clear speech in a quiet room comes out nearly word for word. For names, jargon, accents or noisy audio, choose Accurate: a larger model that takes longer.
Which languages does it understand?
Whisper recognises 99 languages and can detect which one is spoken. It can also turn the speech into English text.
Why does the first run take longer?
The speech model downloads once: Fast is up to 140 MB and Accurate up to 360 MB, depending on your browser. After that it starts in seconds and works offline.
Is there a length limit?
No. Long recordings are transcribed in 30-second steps and the text appears as it goes. Very long files need enough free memory; splitting them with Trim Audio is faster.
03 — Related
Related tools
04 — More
All audio tools