Skip to content

MP3 to text

MP3 to text

To convert an MP3 to text, drop the MP3 on this page, pick the language or leave it on automatic, and start. The transcript appears with timestamps and can be edited and exported as TXT, SRT or VTT. One MP3 up to 15 minutes and 25 MB is free with no account. No conversion to WAV is needed.

Upload an MP3 and get the speech in it back as text, with a timestamp on every line. Fix any line in the editor, then copy it or download it as a text, subtitle or spreadsheet file.

Free preview: one file up to 15 minutes and 25 MB, 3 tries a day, no account needed.

Want to keep your transcripts? Create a free account

Key facts

How to convert an MP3 to text

  1. Upload the MP3. Drop the file into the box.
  2. Choose the language. Pick the language or keep automatic detection.
  3. Start. Wait while it is transcribed.
  4. Edit. Correct any line; click it to hear that part.
  5. Download. Export TXT or timestamped TXT.

Last updated:

What an MP3 is, and why it matters here

An MP3 is compressed audio, and the compression is lossy: the file is small because some detail was thrown away when it was made. For speech that is almost never a problem, but a very low-bitrate MP3, or one that was converted from another lossy file, starts from a worse recording than the original and the transcript reflects that. If you still have the original recording, use it.

Podcasts, calls, voice recordings and music

MP3 is how most podcasts, downloaded interviews, dictation recordings and voicemail exports arrive, so it is the most common thing people want turned into text. Speech transcribes well when it is clear. Singing and music are a different job: lyrics sung over instruments are not what the speech recogniser is built for, so expect poor results there.

Long MP3 files

Without an account the limit is 15 minutes and 25 MB per file. A one-hour lecture saved as a typical-bitrate MP3 is usually well under the size limit but over the duration limit, which is what a free account is for. Splitting a recording into parts is an alternative if you only need a section.

How it works

  1. Add a recording

    Drop in a video or audio file, choose one from your device, or record from the microphone. Nothing to install.

  2. It transcribes

    Speech becomes timestamped text, with speaker labels when more than one person talks.

  3. Read, fix, export

    Click any line to correct it, then download TXT, subtitles, Markdown, JSON or CSV.

Questions

How do I convert an MP3 to text?
Choose or drop the MP3 above, wait for the transcript to appear, read it while the audio is fresh, correct anything wrong, then copy or export it.
Do I need to convert the MP3 to WAV first?
No. MP3 is accepted directly, along with WAV, M4A, AAC, FLAC, OGG, Opus and other formats.
Can it transcribe a song's lyrics?
It is built for spoken words. Sung lyrics over music usually come back incomplete or wrong.
Is it free?
Yes — one file up to 15 minutes and 25 MB with no account, up to 3 tries a day. A free account keeps your transcripts in a library and lifts the guest limits; the current limits and paid plans are on the pricing page.
What bitrate does the MP3 need?
There is no required bitrate. Clear speech at a normal bitrate works; very low bitrates and heavy compression make errors more likely.
Can I transcribe several MP3 files at once?
The no-account preview takes one file at a time. With an account you can upload more files, one after another.
Will it keep the timestamps?
Yes, in the timestamped TXT, SRT, VTT and JSON exports.
Can it handle a podcast episode?
Yes, within the limits: 15 minutes without an account, longer with one.
Can I turn the text into subtitles?
Yes. Export the same transcript as SRT or VTT.

Want your transcripts saved and longer files? Create a free account · See pricing · All use cases

Try it with your file

No account needed for a first transcript.