WAV is what field recorders, podcast studios and audio editors produce: uncompressed and full quality. Upload one and Wave AI gives you a transcript with each speaker and timestamp, plus a summary of what was said.
Drop a WAV file here
Any .wav, up to 200MB (about 20 minutes of CD-quality stereo). Free, no account needed.
If a recording was made for editing rather than sharing, it's probably a WAV:
WAV is uncompressed: CD-quality stereo uses about 10MB a minute, and 24-bit/48kHz stereo about 17MB. Export it as MP3 or FLAC (or as mono, which halves the size) and upload that. The transcript will be just as accurate.
No. Speech recognition gets everything it needs from a standard recording. The extra detail in a 24-bit or 96kHz file makes the upload bigger, not the transcript better.
Upload the mixed track to get one transcript with every speaker labelled. Separate tracks transcribe fine on their own, but each comes back as its own transcript.
Yes. Every line has a timestamp, so you can find a quote and jump to it in your editor. You can also download .srt or .vtt captions when timing is available.
The file is uploaded to temporary storage and transcribed. We may then keep a private copy of the audio and transcript to improve Wave's speech recognition. It's never published. Don't upload recordings you don't want to share with us.
Related: Free Audio Transcription: Transcribe Audio to Text with AI · Audio Transcription Software That Records and Transcribes
Product
Use Cases
Compare
All rights reserved
Made with love in New York City