Rate this page:

LiveAPIClientParameters

Gemini.LiveAPIClient parameters. Can be passed as arguments to the Gemini.createLiveAPIClient method.

Props

apiKey: string | undefined

Optional. Gemini API key. Required for [Backend.GEMINI_API]. Get a Gemini API key here.

backend: Backend

Optional. Backend is the GenAI backend to use for the client. The default value is [Backend.GEMINI_API].

connectConfig: Object

Optional. Session config for the API connection.

credentials: string | undefined

Optional. Google credential file content.

httpOptions: Object

Optional. HTTP options to override. NOTE: the 'baseUrl' parameter will be ignored.

location: string | undefined

Optional. GCP Location/Region for Vertex AI. Required for [Backend.VERTEX_AI]. Generative AI locations.

model: string | undefined

Optional. The model to use for Gemini Live API processing. The default value is gemini-2.0-flash-exp.

onWebSocketClose: (event: WebSocketEvents.CLOSE) => void | undefined

Optional. A callback function that is called when the WebSocket connection is closed.

project: string | undefined

Optional. GCP Project ID for Vertex AI. Required for [Backend.VERTEX_AI]. Find your Project ID here.

statistics: false | undefined | true

Optional. Enables statistics functionality.

trace: false | undefined | true

Optional. Whether to enable the tracing functionality. If tracing is enabled, an URL to the trace file appears in the websocket.created message. The file contains all sent and received WebSocket messages in the plain text format. The file is uploaded to the S3 storage.

Note: Enable this only for diagnostic purposes. You can provide the trace file to our support team to help investigating issues.