Skip to main content

Interface: CustomRealtimeModelConfig

Defined in: packages/sdk/src/types/model-config-types.ts:93

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

Extends​

Properties​

inferenceModel​

inferenceModel: string

Defined in: packages/sdk/src/types/model-config-types.ts:97

inferenceModelConfig?​

optional inferenceModelConfig: ChatModelConfig | null

Defined in: packages/sdk/src/types/model-config-types.ts:98

interruptionSound?​

optional interruptionSound: InterruptionSound | null

Defined in: packages/sdk/src/types/model-config-types.ts:69

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

Inherited from​

BaseRealtimeModelConfig.interruptionSound

interruptionSoundVolume?​

optional interruptionSoundVolume: number | null

Defined in: packages/sdk/src/types/model-config-types.ts:71

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

Inherited from​

BaseRealtimeModelConfig.interruptionSoundVolume

sttConfig?​

optional sttConfig: Record<string, unknown> | null

Defined in: packages/sdk/src/types/model-config-types.ts:95

sttModel?​

optional sttModel: string | null

Defined in: packages/sdk/src/types/model-config-types.ts:94

thinkingSound?​

optional thinkingSound: ThinkingSound | null

Defined in: packages/sdk/src/types/model-config-types.ts:61

Sound to play while the agent is processing tool calls.

Inherited from​

BaseRealtimeModelConfig.thinkingSound

thinkingSoundInitialDelay?​

optional thinkingSoundInitialDelay: number | null

Defined in: packages/sdk/src/types/model-config-types.ts:65

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

Inherited from​

BaseRealtimeModelConfig.thinkingSoundInitialDelay

thinkingSoundVolume?​

optional thinkingSoundVolume: number | null

Defined in: packages/sdk/src/types/model-config-types.ts:63

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

Inherited from​

BaseRealtimeModelConfig.thinkingSoundVolume

thinkingSpeechPhrases?​

optional thinkingSpeechPhrases: string[] | null

Defined in: packages/sdk/src/types/model-config-types.ts:67

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

Inherited from​

BaseRealtimeModelConfig.thinkingSpeechPhrases

ttsModel?​

optional ttsModel: TTSModel | null

Defined in: packages/sdk/src/types/model-config-types.ts:73

TTS model ID in provider:tts:model format (e.g. 'elevenlabs:tts:eleven_flash_v2_5'), or 'native'.

Inherited from​

BaseRealtimeModelConfig.ttsModel

voiceModel?​

optional voiceModel: string | null

Defined in: packages/sdk/src/types/model-config-types.ts:75

Canonical voice identifier (e.g., elevenlabs:voice:catt) that selects the specific agent voice.

Inherited from​

BaseRealtimeModelConfig.voiceModel