|
Silero VAD is an open-source deep learning model developed by the Silero Team. It is designed to detect human speech in audio streams. It acts as an efficient voice activity detector, distinguishing speech from silence or noise.
The integration in Praat uses the whisper.cpp implementation of Silero VAD, with Silero VAD model data compiled into Praat (see Acknowledgments).
© Anastasia Shchupak 2026-03-15