Optional agentOptional agentWhen the model supports it, let an AgentSession push each assistant reply into
agentContext so it is carried into the model's conversation context. Defaults to false;
set true to enable. Prior user turns are carried automatically by the model regardless of
this flag. Ignored on models without context support.
Optional apiHow large each chunk of audio is before being sent to AssemblyAI, in
milliseconds. Corresponds to Python's buffer_size_seconds (seconds there,
ms here per this repo's time-unit convention).
Optional domainOptional endOptional formatOptional inactivitySession inactivity timeout in seconds. AssemblyAI accepts integer values from 5 to 3600; when unset, no inactivity timeout is applied.
Optional keytermsOptional languageOptional maxOptional maxMaximum silence (ms) before end-of-turn is forced regardless of confidence.
Optional minMinimum silence (ms) before a confident end-of-turn is finalized.
Optional modeAccuracy/latency preset for the Universal-3 Pro model family: min_latency, balanced,
or max_accuracy. Explicit turn-silence values still take precedence over mode defaults.
Optional previousOnly supported with the Universal-3 Pro model family. Set at connection time only.
Optional promptOnly supported with the Universal-3 Pro model family.
Optional speakerEnable speaker diarization. Note: AssemblyAI will return per-word speaker
labels, but the JS framework's stt.SpeechData type does not yet expose
a speakerId field (unlike the Python framework), so the labels are not
currently surfaced on emitted events. Setting this to true still has
effect server-side. Once the base SpeechData interface gains speaker
support, #processStreamEvent should forward data.words[].speaker too.
Optional vadOptional voiceIsolate the primary voice and suppress background noise. Connect-time only.
Optional voiceBackground audio suppression aggressiveness, from 0.0 to 1.0. Connect-time only.
Only supported with the Universal-3 Pro model family.