Interface AssemblyAIOptions

Deadline for one streaming connect attempt — socket open and the server's Begin message. Defaults to STT_CONNECT_TIMEOUT_MS (2500 ms), overriding the SDK's own 1000 ms, which a healthy handshake can exceed. 0 waits indefinitely.

Extra connect attempts after a transient failure (timeout, network drop, unexpected close); permanent failures such as auth are never retried. Defaults to STT_CONNECT_MAX_RETRIES (2). 0 disables retries.

Raising either knob widens the worst-case open time ((1 + retries) * connectTimeoutMs plus the retry delays), which has to stay under DEFAULT_SESSION_START_TIMEOUT_MS — see the connect-budget note in sdk/constants.ts.

Minimum end-of-turn silence (ms) before the service commits a final, sent as the min_turn_silence connection parameter. This is where endpointing lives: mid-utterance pauses shorter than this aggregate into one final instead of splitting the request across turns. Defaults to DEFAULT_MIN_TURN_SILENCE_MS (2000).

Streaming speech model. Defaults to "universal-3-5-pro" (Universal-3.5 Pro Real-Time). Arbitrary strings are forwarded to the SDK unchanged.

EU data-residency — routes both streaming and sync transcription to AssemblyAI's EU endpoints (streaming.eu.assemblyai.com / sync.eu.assemblyai.com). Required for EU-region API keys, which the US endpoints reject. Defaults to "us".

Voice focus (voice isolation) mode, sent as the voice_focus connection parameter. Defaults to "near-field" to suppress background noise for close-mic / phone audio. Set to "" (or "off") to disable.