Assembling...
Real-time speech-to-speech foundation model available through Amazon Bedrock. Enables bidirectional streaming voice conversations with native understanding, tool use, and integration with the broader Bedrock agent ecosystem.
Talk naturally with Nova Sonic
Start a conversation and speak freely. The AI will listen and respond naturally — no buttons between messages.
Demo Mode · Voice: Browser
Native speech-to-speech model processes audio without transcription step
First-party Bedrock integration with agents, guardrails, and knowledge bases
Bidirectional streaming supports natural conversational interruptions
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.
// Nova Sonic — Conversational Voice Session
import { VoiceSession } from "@arkitekton/voice";
const session = await VoiceSession.create({
model: "vm-amz-001",
vendor: "amazon",
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);Cloud-native speech services within the AWS ecosystem