The short route
Drop the MP3 onto the page and wait. Processing usually takes about two minutes of wall clock per hour of audio, so a one-hour recording is done in a couple of minutes.
You do not convert the MP3 to another format first, and you do not choose a language — it is detected automatically from 99.
If the MP3 is not on your machine
Paste a link instead: any public audio or video URL works. Or import from Google Drive, including a whole folder of MP3s at once rather than one at a time.
If you want to submit files from your own code rather than a browser, there is an API with keys.
Getting the text in the shape you need
Export as TXT for plain text, DOCX to keep editing in a word processor, SRT or VTT for captions, or JSON if something downstream is going to read it.
Every transcript stays in a searchable Library, so an MP3 you transcribed last month is still findable by what was said in it.
Big files and long ones
One file up to 5 GB, up to 12 hours. An audiobook-length MP3 is inside that. Longer recordings are split before processing on our side — you do not split anything yourself.
What it costs
First transcript free at any length, no card and no account needed to start. Second $0.99, once per email address.
Then minute packs, one-time and with no subscription: $8 / 1,000 minutes, $12 / 2,000 minutes, $24 / 5,000 minutes. Minutes do not expire. Workspace is $19/month for unlimited transcription on the web app.
How to do it
- Open WhipScribe and drag the MP3 onto the page.
- Or paste a public link to the MP3, or import it from Google Drive.
- Wait — usually about two minutes per hour of audio.
- Read the transcript, and the overview, takeaways and chapters written from it.
- Export as TXT, DOCX, SRT, VTT or JSON.