SpeechToSpeechConfig

Signed model, voice, and governance declaration for a chat trigger.

SDK v2026.4.0

Kind: interface

Signature

Example

export interface SpeechToSpeechConfig

providerId (string): Provider identifier resolved by the governed LLM proxy.
model (string): Realtime-capable speech model identifier.
voice (RealtimeVoiceId): Fixed synthesized voice used for a provider session.
requestedMode (SpeechToSpeechMode): Maximum-latency governance path the agent requests.
reasoningEffort (minimal | low | medium | high | xhigh): Bounded provider reasoning effort used for speech turns.
recording (SpeechToSpeechRecording): Whether per-session recording may be offered after tenant and user gates.

RuntimeSessionError

Typed error for invalid or expired runtime sessions.

SpeechToSpeechMode

Governance mode requested by a signed speech-to-speech declaration.