use case · basics
The simplest question a VAD answers. Give Silero a clip and it walks it frame-by-frame, emitting a speech probability for each 32 ms. If enough frames clear the threshold, there's speech. Pick a sample or drop your own.
The bundled Speech clip alone (not the other samples) is a JFK inaugural excerpt (20 January 1961), spoken by John F. Kennedy — public domain, U.S. government work · JFK audio source and attribution record.
← Back to Silero VAD · Next: Practical →