Audio to text
Convert audio to text by dropping the file here. MP3, WAV, M4A, FLAC, OGG and Opus all work, and the spoken language is detected for you.
Transcription is free within your daily minutes
A subtitle file dropped here is converted instead.
- File
- Format
- Cues
- Size
Read as — change it
The preview below re-renders as soon as you change this.
This format stores times as frame numbers, so it has no meaning without a rate. We don't guess one.
Nothing has changed yet.
No cues to show yet.
Drop an audio file and get back what was said, as plain text or as a subtitle file with timings. Use it to turn audio into text online: interviews, lectures and voice notes come back as an audio transcript you can copy, with nothing to install. If the recording is already online you don't need the file at all: paste the link into the YouTube or podcast transcript page instead.
Questions
How do I transcribe an audio file for free?
Drop it above and the text comes back on the page, ready to copy or download. It's free for 90 minutes of audio a day, and there's no account to make.
Can I turn audio into text online?
Yes: you can transcribe online right here, with no app to install and no account. Drop the file above and the audio transcript appears on the page, ready to copy or to download as text, Word, PDF or subtitles.
Which audio formats can I use?
MP3, WAV, M4A, AAC, FLAC, OGG, OGA and Opus. AMR files from some older phones aren't supported, so convert those to MP3 first.
Does it work for languages other than English?
Yes. The spoken language is detected automatically, so there's nothing to set. Clear recordings give the best results in any language.
Is there a page for my language?
Yes, if it's one of the 78 languages with a page of its own, from Afrikaans to Yoruba, listed under transcription by language on the tools page. Each one expects its own language, so a short clip isn't mistaken for a neighbouring one.
How long can the recording be?
Up to 90 minutes, and the file has to be under 95 MB. A 90-minute MP3 at 128 kbps is about 86 MB, so it fits. A WAV of the same length doesn't; see WAV to text.
Does it tell speakers apart?
No. You get the words in order, without speaker names.