Streaming Tts And Websocket

Agent opens a connection to /tts/websocket but puts the API key only in a later message body, not where the WebSocket handshake expects it.

Authenticate the /tts/websocket connection per docs (API key + Cartesia-Version supplied where the handshake requires, e.g. query param or header per the documented scheme). Establish the socket before sending synthesis frames; handle a rejected handshake distinctly from a mid-stream drop.

Agent needs full-duplex behavior (push text incrementally AND cancel/flush mid-stream) but builds it on /tts/sse, which is one-directional.

Use /tts/websocket for bidirectional/interactive cases (incremental input, flush, cancellation, continuations); use /tts/sse for simple one-direction server-streamed audio of a fixed transcript. Pick the transport from the interaction requirements, not familiarity.

Agent streams a multi-sentence utterance as several inputs over one socket but uses a fresh context_id per chunk, breaking prosodic continuity.

Reuse a stable context_id across inputs that belong to the same utterance so Sonic continues prosody/state coherently. Allocate a new context_id only when a genuinely new utterance begins. Track context_id lifecycle explicitly.