Re-listening to an hour-long interview to find one quote, or typing up a lecture by hand, is slow and tedious. Audio to Text turns a recording into text in about a minute.
Upload a file: a voice message, meeting recording, interview, lecture, podcast or video. MP3, WAV, M4A, OGG, FLAC, WebM and MP4 up to 25 MB are supported. Speech is recognized by OpenAI Whisper, one of the most accurate models: it detects the language on its own and adds punctuation.
The text appears on the page — copy it in one click and paste it into a document, notes or a script. The price is flat, and if no speech is recognized, you are not charged.