Create realtime TTS session
Create a short-lived browser-safe token for the realtime text-to-speech WebSocket. This HTTP operation only creates the session. Official SDKs and the CLI prefer the optional query-free direct_websocket_url and fall back to websocket_url; wait for session.ready, and then exchange turn events and binary PCM audio. While no turn is active, send session.update with non-empty instructions (up to 1,000 characters) and wait for session.updated; the confirmed instructions apply starting with the next turn. See the Realtime TTS WebSocket guide for complete raw WebSocket, SDK, browser playback, and CLI examples.
Authorizations
Breeze Developer API key.
Path Parameters
Voice identifier to synthesize. Use GET /v1/voices to discover available IDs.
Body
Optional model identifier to use for realtime synthesis.
1 - 120Optional ISO 639-1 two-letter language code. The selected model must list the code in supported_languages.
2^[A-Za-z]{2}$Optional initial performance instructions for the realtime session. Use Chinese for Chinese TTS and English for English or any other language; realtime sessions do not translate instructions automatically. While the WebSocket is idle, send session.update to change them; after session.updated confirms the change, the new instructions apply starting with the next turn.
Optional realtime voice settings.
Idle timeout for the WebSocket session. Defaults to 30 seconds and is capped at 180 seconds.
1 <= x <= 180Whether realtime turns should be stored in generation history.
Response
Realtime WebSocket session token and compatible transport URLs.
Short-lived token for browser WebSocket connections.
WebSocket URL including the client_secret query parameter.
ISO-8601 expiration timestamp for the client secret.
Optional direct WebSocket URL without credentials in its query. Authenticate with the documented WebSocket subprotocols.
Fixed realtime audio stream format.

