Skip to main content

BaseRealtimeModelConfig

@gravity-rail/sdk

@gravity-rail/sdk / BaseRealtimeModelConfig

Interface: BaseRealtimeModelConfig

Base configuration for all realtime models. Contains common fields that apply to all realtime model providers.

Extended by​

Properties​

inactiveConfig?​

optional inactiveConfig: Record<string, unknown> | null

Settings belonging to the voice architecture that is NOT currently selected, parked so switching between the composable stack and a native speech-to-speech model is lossless and reversible.

Declared on the base because the native schemas set extra="forbid" server-side: an undeclared key would be rejected on save. Written and read only by the switch itself (reconcile_realtime_model_config on the server, parkComposableConfig / restoreComposableConfig in the editor). Nothing at call time reads it — it is a holding area, never live configuration.

interruptionSound?​

optional interruptionSound: InterruptionSound | null

Sound to play when user stops speaking after interrupting the assistant. Provides immediate auditory feedback that input was received. Default: none.

interruptionSoundVolume?​

optional interruptionSoundVolume: number | null

Volume level for the interruption sound (0-100). 0 means muted. Missing or null means full volume (100).

thinkingSound?​

optional thinkingSound: ThinkingSound | null

Sound to play while the agent is processing tool calls.

thinkingSoundInitialDelay?​

optional thinkingSoundInitialDelay: number | null

Initial delay in milliseconds before playing thinking sound. Prevents needless interruption on short tool calls. Default: 500ms.

thinkingSoundVolume?​

optional thinkingSoundVolume: number | null

Volume level for the thinking sound (0-100). 0 means muted. Missing or null means full volume (100).

thinkingSpeechPhrases?​

optional thinkingSpeechPhrases: string[] | null

When thinkingSound is 'speech', one of these phrases is spoken while the agent runs a tool. Phrases rotate round-robin per session.

ttsModel?​

optional ttsModel: TTSModel | null

TTS model ID in provider:tts:model format (e.g. 'xai:tts:v1'), or 'native'.

voiceModel?​

optional voiceModel: string | null

Canonical voice identifier (e.g., xai:voice:lux) that selects the specific agent voice.