SileroVAD Extension

Silero Voice Activity Detection (VAD) is a machine learning-based tool designed to identify segments of audio that contain human speech. It is highly efficient, lightweight, and capable of operating in real-time, making it ideal for applications such as speech recognition, telecommunication systems, and audio processing pipelines.

Dependencies

The SileroVAD extension requires the ONNX extension to be loaded.

SileroVAD Node

The voice activity detector (VAD) node uses SileroVAD to detect the presence of voice activity in the audio signal.

Configuration

Name	Type	Description
frameSize	int	The size of the audio buffer (in number of frames) used for processing.
threshold	float	The sensitivity threshold for detecting voice activity. Higher values make detection stricter.
minSilenceDurationMs	int	The minimum duration of silence (in milliseconds) required to consider speech as ended.
speechPadMs	int	The amount of padding (in milliseconds) added before and after detected speech segments.

Values

This object does not provide any values.

Actions

This object does not provide any actions.

Events

Name	Data	Description
start	Double	Indicates when voice activity starts.
end	Double	Indicates when voice activity ends.

Download

You can find the download links for this extension on our Downloads page.