Do 24-bit or 32-bit float WAVs work?

Yes: 8, 16, 24 and 32-bit integer and 32/64-bit float PCM, mono or multichannel, at any sample rate. Channels are mixed down and resampled for the model automatically.

Is a huge WAV slow to start?

No. Only a slice is read at a time, so transcription starts within seconds whatever the file size.

All tools

WAV to text — transcribe uncompressed audio of any length

WAV is the format of field recorders, studio exports and dictation machines — large, uncompressed, and often long. Here it is read straight off your disk a slice at a time, so a three-hour WAV is no harder than a three-minute one.

Drop an audio or video file here

MP3, M4A, WAV, MP4, OGG, FLAC, WebM — any length

Spoken language

Transcribed in your browser. The file never leaves your device.

Recording 0:00

Click any line to play it.

About WAV files

Your browser: checking…
Audio inside: PCM
Typical size: ≈ 10 MB per minute
Length: Read in small pieces, so any length works

How it works

Drop an audio or video file into the box above, or choose one from your device.
The speech model loads in your browser and the text appears as it is transcribed. The file is never uploaded.
Copy the transcript, or download it as TXT or as SRT subtitles.

FAQ

Do 24-bit or 32-bit float WAVs work?: Yes: 8, 16, 24 and 32-bit integer and 32/64-bit float PCM, mono or multichannel, at any sample rate. Channels are mixed down and resampled for the model automatically.
Is a huge WAV slow to start?: No. Only a slice is read at a time, so transcription starts within seconds whatever the file size.