MP3toText

MP3toText turns audio and video recordings into text in the browser, with nothing to install. Upload an MP3, M4A, WAV, AAC, FLAC or OGG file, or a video such as MP4, MOV, MKV or WEBM, and the transcript comes back with a timestamp on every line and each speaker labelled separately.

The spoken language is detected automatically across 90+ languages; the tool transcribes in the language that was spoken and does not translate. Files can be up to 2 GB and 4 hours long, and a one-hour recording usually finishes in a few minutes. Transcripts export as TXT, SRT or VTT, and you choose whether speaker labels and timestamps are included.

Files under 30 minutes need no account. Longer files need a free Google sign-in, which gives four hours of audio a day (up to 10 hours in total). Hour packs and monthly plans are available for more. Recordings are sent over an encrypted connection and are not used to train models.

Useful for interviews, meetings, lectures, podcasts and voice memos.