mp3 to text
Podcasts, lectures, voice memos, calls — drop the audio file and get the text. No account, no minutes counter, no upload.
Audio formats that work
MP3, M4A/AAC, WAV and FLAC work in every modern browser. OGG/Opus works in Chrome, Edge and Firefox, and in recent Safari versions. Anything your browser can play, it can usually transcribe.
Stereo files are mixed down to mono and resampled to 16 kHz automatically, which is what the Whisper model was trained on — you don't need to prepare the file.
Accuracy you can expect
Whisper is one of the best open speech models, but the versions small enough to run in a browser are less accurate than big paid cloud services. Clear speech with one speaker comes out very well; noisy rooms, overlapping voices and heavy music make it harder.
Always proof-read names, numbers and jargon before using the transcript for anything important.
Private by design
Lots of free transcription sites limit you to a few minutes and keep your recordings. Here the model is downloaded to your browser and cached, and all processing happens on your device. Close the tab and nothing remains anywhere but your own downloads.
Turning a transcript into notes
A raw transcript is a wall of text. Switch off timestamps to get one clean paragraph, copy it, and run it through our AI rewriter with “make it shorter” to turn a 30-minute lecture into a quick summary — still all on your device. For interviews, keep timestamps on so you can jump back to the exact moment in the recording when you quote someone.
What you get
- Plain text — copy it or download a .txt file.
- SRT and VTT subtitles with start and end times for every phrase.
- Optional English translation of speech in other languages.
Frequently asked questions
Is there a time limit?
No limit from us. Very long files just take longer and use more memory; for multi-hour recordings, a laptop works best.
Can I transcribe a phone call recording?
Yes, if you have the file. Make sure you have everyone's consent to record and transcribe the call where the law requires it.
Does it add punctuation?
Yes — Whisper writes punctuation and capitalisation as part of the transcript.
Is my file uploaded to a server?
No. Everything runs in your browser. Only the Whisper AI model is downloaded (once) from Hugging Face and cached.
Is it free?
Yes — no sign-up, no minutes limit, no watermark. Your own device does the work, so there's nothing for us to charge for.