Azure Voice Live API

MicrosoftConversationalMultilingualPreviewProprietaryvm-ms-001

About

Full-duplex conversational voice API within Azure AI Services enabling real-time voice agents. Integrates with Azure OpenAI, Cognitive Search, and enterprise identity for secure, compliant voice experiences.

Capabilities (5)

Full-duplex dialogue

Azure OpenAI integration

Enterprise identity (Entra)

Cognitive Search grounding

Compliance controls

Talk naturally with Azure Voice Live API

Start a conversation and speak freely. The AI will listen and respond naturally — no buttons between messages.

Demo Mode · Voice: Browser

Key Highlights

Deep integration with Azure OpenAI and enterprise identity via Entra ID

Built-in compliance controls for regulated industries

Cognitive Search grounding provides RAG-powered voice responses

Use Cases

Customer Support Agents

Deploy AI voice agents that handle customer inquiries with natural conversation flow and real-time responses.

Virtual Assistants

Build always-on voice assistants for enterprise applications with full-duplex capabilities.

Telehealth & Consultation

Enable voice-first healthcare consultations with HIPAA-compliant conversational AI.

Interactive Voice Response

Replace traditional IVR menus with natural language voice agents that understand intent.

Code Example

// Azure Voice Live API — Conversational Voice Session
import { VoiceSession } from "@arkitekton/voice";

const session = await VoiceSession.create({
  model: "vm-ms-001",
  vendor: "microsoft",
  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);

Related Models

PersonaPlex 7B

NVIDIA

Riva

NVIDIA

ACE (Avatar Cloud Engine)

NVIDIA

gpt-4o-realtime

OpenAI

gpt-4o-mini-realtime

OpenAI

gpt-4o-mini-transcribe

OpenAI

Quick Stats

Latency<500ms end-to-end

Languages60 supported

LicenseProprietary

PricingAzure consumption-based

StatusPreview

Vendor

Microsoft

Enterprise speech services across Azure and research labs

View all Microsoft models

Documentation

View on Microsoft Site

Customer Support Agents

Deploy AI voice agents that handle customer inquiries with natural conversation flow and real-time responses.

Virtual Assistants

Build always-on voice assistants for enterprise applications with full-duplex capabilities.

Telehealth & Consultation

Enable voice-first healthcare consultations with HIPAA-compliant conversational AI.

Interactive Voice Response

Replace traditional IVR menus with natural language voice agents that understand intent.

Code Example

// Azure Voice Live API — Conversational Voice Session
import { VoiceSession } from "@arkitekton/voice";

const session = await VoiceSession.create({
  model: "vm-ms-001",
  vendor: "microsoft",
  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);