Optional apiOptional audioAudio playback speed
Optional baseOptional boostedKeywords to boost in speech recognition
Optional connConnection options for the API connection
Optional generateAuto-generate poke text when user is silent
Optional generateWhen true, the welcome message will be automatically generated and welcomeMessage will be ignored
Optional languages?: string[]ISO 639-1 language codes the agent should recognize and speak
Optional model?: stringThe name of the model to use. Defaults to 'merritt'
Optional noSeconds of silence before ending conversation
Optional noSeconds of silence before sending poke message
Optional noPoke message text (ignored when generateNoInputPokeText is true)
Optional phonicPhonic agent to use for the conversation. Options explicitly set here will override the agent settings.
Optional phonicPhonic tool names available to the assistant
Optional project?: stringProject name to use for the conversation. Defaults to main
Optional voice?: stringVoice ID for agent outputs
Optional welcomeWelcome message for the agent to say when the conversation starts. Ignored when generateWelcomeMessage is true
The model name/identifier used by this realtime model
Phonic API key. If not provided, will attempt to read from PHONIC_API_KEY environment variable