MP3 to text: convert an audio recording to a transcript
Upload an MP3 and get the words as text, split by speaker, with timestamps, in 99 languages.

Converting MP3 to text takes a few minutes: upload the file and voxnoto returns a transcript you can read, search and export. MP3 is the format most recorders, phones and podcast tools save to, so it's usually the file you already have.
How to convert an MP3 to text in four steps
Open voxnoto and click Upload. Drag the MP3 in, or pick it from your computer or phone.
Wait a few minutes. You can close the tab and come back.
Read the transcript, rename the speakers, correct any word in place.
Export as TXT, or translate the text first.
Where MP3 files come from
Voice recorders and phones. Most handheld recorders and Android apps save MP3 by default. Whatever the app called the file, if it plays, voxnoto can read it.
Downloaded and shared audio. Podcast episodes, lecture recordings, files a colleague sent you, MP3 is the format that travels between people and platforms without conversion.
Exports from other tools. Call recorders, editing software and conference platforms usually offer MP3 as an export option.
What you get back
The full transcript. Every word, split by speaker, with timestamps against each turn.
A summary. For a long recording, an interview, a lecture, a meeting, the summary is the part most people read.
A translation. Transcribe in 99 languages and translate the transcript.
Export. Download the text as TXT and take it into any document or notes app.

Getting a cleaner transcript from an MP3
- Use the original file. Each re-compression loses a little of the speech.
- Very low-bitrate files, 32 kbps and below, transcribe noticeably worse; if you can re-export at a higher bitrate, do.
- Trim the silence at the start so it doesn't eat into your minutes.
- If several people speak, ask each to say their name once. Renaming speakers afterwards then takes seconds.
Other formats
If your file isn't an MP3, that's fine, voxnoto also reads M4A, WAV, AAC, OGG, OPUS and WMA, and it transcribes video files like MP4 and MOV by reading their audio track.
Questions and answers
How do I convert an MP3 to text?
Upload the file to voxnoto. The transcript is ready in a few minutes.
How long can the MP3 be?
Up to 8 hours per file.
Which languages does it support?
Speech is recognized in 99 languages, and the spoken language is detected automatically, so there is nothing to set up. A finished transcript can be translated into 22 languages in one click.
Can I convert an MP3 to text for free?
The free plan covers 10 minutes of transcription every day.
Can I edit the transcript?
Yes, including speaker names.
Does the bitrate affect accuracy?
Yes. Very compressed files give a weaker transcript than the original recording.
Did not find your answer?Browse all questionsEmail support


