@langwatch/scenario
    Preparing search index...

    Class WebRTCVadFallback

    Incremental VAD over PCM16 @ 24 kHz mono audio.

    Feed chunks via process; the configured onSpeechStart / onSpeechEnd callbacks fire when the speech/silence transitions stabilise. The detector is purely sample-driven — no async, no timers — so a single instance is safe to share across an entire scenario as long as one adapter feeds it.

    Index

    Constructors

    Accessors

    Methods

    Constructors

    Accessors

    Methods