How do I convert an MP3 to text?

Drop the MP3, choose the language spoken and click Transcribe. A few minutes later the text is ready to copy, or to download as TXT, SRT or VTT.

Can I transcribe an iPhone voice memo?

Yes. Voice memos are M4A files: share them from the Voice Memos app to your computer (or open this page on the phone) and drop them here.

How long does it take?

In Fast mode, about a quarter of the audio's length on a recent computer (15 minutes for 1 hour). Precise mode is 2 to 4 times slower without a graphics card. Transcribing only a part with the handles is faster.

Is my recording uploaded?

No. Whisper, the speech recognition model by OpenAI, runs inside your browser (Transformers.js). The audio never leaves your device; only the model itself is downloaded, once.

Which languages are supported?

French, English, Spanish, German, Italian, Portuguese, Dutch, Arabic, Turkish, Polish, Russian, Ukrainian, Chinese, Japanese, Korean, Hindi and Swedish. Choose the language spoken before transcribing.

My podcast has music: is it a problem?

Music-only passages are skipped when silent, but music under speech can confuse the model. The Precise model handles it better; re-read the result around jingles.

AI · 100% local

MP3 to Text Converter

Transcribe voice memos, interviews, podcasts and recorded lectures — MP3, WAV, M4A, OGG, FLAC — into text, privately, on your device.

100% local

Model

Language spoken

Drag & drop an audio or video file here

or browse your files

MP3, WAV, M4A, MP4, MOV, WebM… · Max 100 MB per file

Transcript

The transcript will appear here. Download it as text (TXT) or subtitles (SRT, VTT).

Learn more

Everything about MP3 to text

Voice recordings become text

Interviews, focus groups, lectures, sermons, voice memos, podcasts: anything spoken and recorded can be turned into text you can read, search, quote and share — without typing it again.

Every audio format

MP3 is the most common, but WAV (recorders), M4A (iPhone voice memos), OGG, OPUS (messaging apps), AAC and FLAC work too. FFmpeg decodes them all in your browser before the transcription.

Confidential by design

Recordings of interviews or patients are sensitive. Here the audio is never uploaded: once the model is downloaded, the transcription even works offline.

How it works

How to convert MP3 to text

Drop your recording
MP3, WAV, M4A (voice memos), OGG, FLAC, AAC…
Choose language and model
Fast for a clear voice, Precise for accents, noise or several people.
Copy or download
Copy the text or download TXT, SRT or VTT.

Practical guides

Tips & guides

Interviews and voice memos

Journalists, students, researchers: transcribe the recording, then mark the quotes in the text instead of replaying the audio ten times.

Dictated notes and ideas become searchable text you can paste into your notes app.

Pro tip

100% private

The speech model runs in your browser: your recording is never uploaded, stored or listened to by anyone.

Safe for interviews, medical or legal recordings, meetings and anything confidential.

Privacy

Frequently asked questions

Everything about transcribing MP3