← All models · Whisper

use case · basics

Basics: one clip, a timestamped transcript

This is the whole idea in its simplest form. Give Whisper an audio clip; it hands back the words that were said, each tagged with the moment it happened. Pick a sample or upload your own file.

Preparing audio and the on-device model…

or a sample:

Bundled JFK inaugural excerpt (20 January 1961), spoken by John F. Kennedy — public domain, U.S. government work · JFK audio source and attribution record. LibriSpeech: reader Paul-Gabriel Wiener, OpenSLR SLR12, CC BY 4.0.

JFK — inaugural (11s)

Transcript

Transcribe a clip to see the text here.

Word timestamps

Each word Whisper hears gets its own start/end time — they'll appear here.

← Back to Whisper · Next: Practical →