Audio transcription
Upload an audio file and get an editable transcript, with SRT and VTT subtitles when timings are available.
Audio inputPrice shown before you run
- Accepted: MP3, WAV, M4A, FLAC. Up to 5 MB and 180 seconds (3 min).
- Timestamps come from the speech model; speakers are not identified.
1. Your input
2. Your result
Working on it…
This usually takes a few seconds. You can cancel, but the AI service may still finish work it already started.
You can edit this text. Copy and download use your edited version.
No subtitle timings were returned for this file.
AI can make mistakes. Check results before you use them.
What you get
- result
- An editable transcript with copy and .txt download, plus .srt and .vtt subtitle files.
About this tool
Transcribes speech with OpenAI Whisper running on Cloudflare. Timestamps for SRT and VTT subtitles come from the model itself. Speakers are not identified.
Limitations to keep in mind
- Background noise, accents and overlapping speakers reduce accuracy.
- Names and technical terms may be misspelled: review the transcript.
- There is no speaker labelling.
- Files are limited in size and length.
Frequently asked questions
Which formats work?
MP3, WAV, M4A and FLAC. The exact size and length limits are shown above the upload box.
Is my audio kept?
It is sent to the speech model and not stored on this site.