Build a Voice Agent

Configure the voice agent and sets the input and output audio formats

Send a message to give additional instructions to the Think model in the middle of a conversation

Send a message to change the Speak model in the middle of a conversation

Send a message to change the Speak model in the middle of a conversation

Configure the voice agent and configure the function call response

Send messages ensuring uninterrupted communication for your agent

Receive injection refused message

Receive a welcome message from the server to confirm the websocket has opened

Confirm the server has successfully received and applied the Settings Configuration message

Conversation Text facilitates real-time communication by relaying spoken statements from both the user and the assistant

User Started Speaking notifies the client that the user has begun speaking

Agent Thinking informs the client when the agent is processing information

Request to call a function by sending a Function Call Request message

Provides insights into function call workflows to assist in debugging

Get notified when the server begins streaming an agent’s audio response for playback

Get signals that the server has finished sending the final audio segment to the client

Receive an error message from the server when an error occurs