Audio to Text, with a Summary

Upload a recording – a lecture, a meeting, a podcast, a voice note – and get the key points with the minute each was said, and the full text under them.

Drop your recording here

mp3, m4a, wav, aac, ogg, mp4, mov, webm, mkv, avimp3, m4a, wav, mp4, mov, webm and more

audio and video · up to 4 hours · up to 2 GB · first 10 minutes free – one of your 2 free videos a day

YouTube and Shorts read the captions. TikTok and Reels are transcribed from the audio.

What one audio file gives you

  • What do I get?An AI summary of the recording with a timestamp on every point, the full text with timestamps, and answers to your questions about it.
  • What is free?Once a day, the summary and the text of the first 10 minutes of any file – a file up to 10 minutes is free whole. No account needed.
  • What does the whole file cost?5 credits a minute for the summary and the text together – an hour is 300 credits. You see the price before anything is charged.
  • Which files?MP3, M4A, WAV, AAC, OGG, FLAC and more, up to 4 hours and 2 GB.
  • Who can see it?Only you. The file is deleted as soon as the speech is recognised; the text stays in your history and never in a shared cache.

How to turn audio into text and a summary

  1. Choose the audio file above – its length and the price appear at once.
  2. Start the free preview of the first 10 minutes, or the whole file for the price shown.
  3. Read the summary with its timestamps, then the full text, and ask a question about it.

A summary of any recording, with the minute of every point

Meetings, lectures, interviews, podcasts and voice notes are long, and what you need from them is usually a few minutes of it. The summary lists the key points in the order they were said, each ending with its timestamp, so you can check any of them against the recording or jump straight to the part that matters.

Why the summary comes first

An hour of audio takes an hour to listen to and about two minutes to read as a summary. So the summary is what you get first – the key points in order, each with the minute it was said – and the full text is right under it for when you need the exact words. Both come from one recognition, charged once.

Frequently asked questions

How do I convert audio to text?

Choose the file on this page. Its length is read in your browser, the file goes up, the speech is recognised and the summary is written from it, with the full text under the summary. A one-hour recording usually takes a few minutes.

Is it free?

Once a day the first 10 minutes of any file are free – the summary and the text – with no account, and a file up to 10 minutes long is free whole. The whole of a longer file is 5 credits a minute, from a plan or a credit pack.

How long can the recording be?

Up to 4 hours and 2 GB. A lecture, a whole meeting or a long podcast episode fits.

Which languages does it work with?

The speech is recognised in the language it is spoken in, and the summary is written in that language. Once it is ready, you can switch the summary to any of 14 languages – free, with the timestamps kept.

Is my file private?

Yes. Only you can see the result. The file goes straight to our storage, is deleted as soon as the speech is recognised, and an upload you abandon is deleted within a day.

What if the file is longer than it says?

The price comes from the length your browser reads. If recognition finds the recording longer, the difference is charged; if it is shorter, nothing changes. If anything fails on our side, the credits come back.

More tools