Unified voice agent API combining Deepgram's Nova-3 ASR and Aura TTS with LLM orchestration. Handles turn-taking, barge-in detection, and end-of-speech events in a single WebSocket connection for building voice agents.
Talk naturally with Deepgram Agent API
Start a conversation and speak freely. The AI will listen and respond naturally — no buttons between messages.
Demo Mode · Voice: Browser
Single WebSocket connection for complete voice agent pipeline
Built-in barge-in detection and adaptive turn management
Combines best-in-class ASR and TTS in one developer-friendly API
Deploy AI voice agents that handle customer inquiries with natural conversation flow and real-time responses.
Build always-on voice assistants for enterprise applications with full-duplex capabilities.
Enable voice-first healthcare consultations with HIPAA-compliant conversational AI.
Replace traditional IVR menus with natural language voice agents that understand intent.
// Deepgram Agent API — Conversational Voice Session
import { VoiceSession } from "@arkitekton/voice";
const session = await VoiceSession.create({
model: "vm-dg-004",
vendor: "deepgram",
config: {
fullDuplex: true,
language: "en-US",
turnDetection: "server_vad",
},
});
session.on("speech_started", () => {
console.log("Agent is speaking...");
});
session.on("transcript", (text) => {
console.log("User said:", text);
});
// Connect to audio stream
const mic = await navigator.mediaDevices.getUserMedia({ audio: true });
session.connect(mic);End-to-end deep learning ASR and TTS built for developers