Member Junction
    Preparing search index...

    A single diarized transcript segment fed into the policy.

    Produced from the bridge's inbound transcript stream. SpeakerLabel/IsAgent come from the provider's diarization; EndMs lets the policy compute silence windows deterministically.

    interface TurnTranscriptSegment {
        EndMs?: number;
        IsAgent?: boolean;
        SpeakerLabel?: string;
        Text: string;
    }
    Index

    Properties

    EndMs?: number

    Epoch-millisecond timestamp at which this segment's speech ENDED. Used to measure the silence window since the last human speech. When omitted, the policy treats the clock's now() as the end time (i.e. no measurable silence yet).

    IsAgent?: boolean

    Whether the speaker of this segment is an agent bot (excluded from "addressed me" detection).

    SpeakerLabel?: string

    The diarized speaker label, when the provider supports it (e.g. a participant id or name).

    Text: string

    The transcribed text of this segment.