@langwatch/scenario
    Preparing search index...

    Variable DEFAULT_SPEECH_GATE_RMS_THRESHOLDConst

    DEFAULT_SPEECH_GATE_RMS_THRESHOLD: 800

    RMS (int16 scale) at or above which a chunk counts as speech.

    Measured on a real Twilio a-leg call against an ElevenLabs callee (100 ms windows, int16 scale after the SDK's own µ-law→PCM16 24 kHz path, which applies no gain): between-utterance noise p95 ≈ 740 (-33 dBFS), speech p10 ≈ 940 (-31 dBFS), p50 ≈ 1380 (-27.5 dBFS). The margin is thin, which is why the gate ALSO needs DEFAULT_SPEECH_GATE_HANGOVER_MS: speech dips under the threshold for up to ~200 ms on plosives and breaths, and a bare threshold would split one utterance into hundreds of fragments. Tune via speechGate.rmsThreshold on the adapter options.