All tools

Audio to text

Turn an MP3, M4A or WAV recording into text and subtitles.

or drop it hereMP3, M4A, WAV, OGG or a video file with sound, up to about 60 minutes each. You can choose up to 20 files at once.

Speech recognition runs in your browser with OpenAI Whisper (open source). The audio never leaves this device. The program (from jsDelivr) and the speech model (from Hugging Face) are downloaded once and then kept by your browser. Check names and numbers in the result.

More tools