Voice Agent Api

Operator opens wss://agent.deepgram.com/agent (or documented endpoint) and sends a SettingsConfiguration message defining Aura voice, Nova STT, and an LLM brain. [REQUIRES-VERIFICATION on current endpoint host/path.]

Send a single configuration message at session start with audio (encoding, sample_rate), agent.listen (STT model), agent.think (LLM provider/model, system prompt), agent.speak (Aura voice). Validate the schema against current docs — fields shift across versions.

Operator configures agent.think with a third-party LLM (e.g., OpenAI GPT, Anthropic Claude) routed through Deepgram's brain plumbing.

Set agent.think.provider and agent.think.model per documented options. Provide the system prompt under agent.think.instructions (or equivalent). BYO-key flows require credential configuration per docs [REQUIRES-VERIFICATION on current BYOK support]. Pin model id; do not float.

User starts speaking while the agent is mid-utterance. The voice agent pipeline must stop TTS and process user audio.

Server emits a turn-event (e.g., UserStartedSpeaking) when STT detects speech onset. Stop playing buffered TTS audio immediately on receipt and flush any local audio queue. Send tts.cancel or close the TTS sub-stream per the agent contract.