Interface AMDOptions

Overall detection budget. When waitUntilFinished is true and speech has been heard, this no longer forces emission; AMD keeps waiting for the greeting to finish before releasing the verdict.

Silence after a short greeting before settling as HUMAN.

Speech longer than this is treated as machine-like (skips the short-greeting heuristic).

LLM used to classify call greetings.

• LLM instance: used as-is (caller-owned; AMD will not close it).
• string: treated as a Cloud Inference model id (e.g. 'openai/gpt-4o-mini') and an inference LLM is constructed (AMD-owned).
• undefined (default): auto-select — if LiveKit Cloud inference credentials are available in the environment, uses 'google/gemini-3.1-flash-lite' via the inference gateway; otherwise falls back to the session's own LLM.

Silence after machine-like speech before opening the silence gate.

Fallback end-of-turn delay (ms). When the session turn detector never commits a turn, this synthetic backstop, armed when speech ends or a final transcript arrives, sets the end-of-turn so a gated verdict can still emit. Defaults to the running session activity's endpointing maxDelay (so the backstop tracks the real turn detector), or DEFAULT_MAX_ENDPOINTING_DELAY_MS when no activity is available. Mirrors python max_endpointing_delay.

If no speech is heard within this window, settle as UNCERTAIN (not a machine, so no interrupt).

Restrict AMD to a specific participant. Used to filter the waitForTrackPublication gate (see python detector.py) and span attribution. When unset, AMD binds to whichever participant the session is linked to.

Override the AMD classification system prompt.

Dedicated STT used to transcribe call audio for AMD.

• STT instance: used as-is (caller-owned; AMD will not close it).
• string: treated as a Cloud Inference model id (e.g. 'cartesia/ink-whisper') and an inference STT is constructed (AMD-owned).
• undefined (default): auto-select — if LiveKit Cloud inference credentials are available in the environment, uses 'cartesia/ink-whisper' via the inference gateway; otherwise reuses the session's existing STT transcripts.

If true, do not log a warning when the resolved LLM is not among the bundled AMD-tested model strings. Has no effect on classification behavior.

If true, once any speech has been heard, detectionTimeoutMs no longer forces emission. AMD waits for post-speech silence and either a session end-of-turn signal or the synthetic maxEndpointingDelayMs backstop before emitting. Useful for outbound voicemail flows where leaving a message early would overlap the greeting. noSpeechTimeoutMs (uncertain) still fires normally when no audio is heard. Continuous speech without a speech-end or end-of-turn can therefore extend detection beyond detectionTimeoutMs; set this to false when detectionTimeoutMs should remain a hard cap after speech starts. Defaults to true. Mirrors python detector.py wait_until_finished.