The version of the Cartesia model to use.

Stream Speech

Connect to Cartesia over a WebSocket and generate speech from a transcript using a given voice and model. The audio is streamed out as Base64-encoded raw bytes.

A unique identifier for the requests belonging to this context. Context id must consist of only alphanumeric characters, hyphens, and underscores.

The maximum duration of the audio in seconds.

URL	wss://api.cartesia.ai/tts/websocket
Method	GET
Status	101 Switching Protocols