@azure/ai-voicelive (JavaScript/TypeScript)

SDK de IA de voz em tempo real para criar assistentes de voz bidirecionais com Azure AI em ambientes Node.js e de navegador.

Instalação

npm install @azure/ai-voicelive @azure/identity
# TypeScript users
npm install @types/node

Versão Atual: 1.0.0-beta.3

Ambientes Suportados:

• Versões LTS do Node.js (20+)
• Navegadores modernos (Chrome, Firefox, Safari, Edge)

Variáveis de Ambiente

AZURE_VOICELIVE_ENDPOINT=https://<resource>.cognitiveservices.azure.com
# Optional: API key if not using Entra ID
AZURE_VOICELIVE_API_KEY=<your-api-key>
# Optional: Logging
AZURE_LOG_LEVEL=info

Autenticação

Microsoft Entra ID (Recomendado)

import { DefaultAzureCredential } from "@azure/identity";
import { VoiceLiveClient } from "@azure/ai-voicelive";

const credential = new DefaultAzureCredential();
const endpoint = "https://your-resource.cognitiveservices.azure.com";

const client = new VoiceLiveClient(endpoint, credential);

Chave de API

import { AzureKeyCredential } from "@azure/core-auth";
import { VoiceLiveClient } from "@azure/ai-voicelive";

const endpoint = "https://your-resource.cognitiveservices.azure.com";
const credential = new AzureKeyCredential("your-api-key");

const client = new VoiceLiveClient(endpoint, credential);

Hierarquia de Clientes

VoiceLiveClient
└── VoiceLiveSession (WebSocket connection)
    ├── updateSession()      → Configure session options
    ├── subscribe()          → Event handlers (Azure SDK pattern)
    ├── sendAudio()          → Stream audio input
    ├── addConversationItem() → Add messages/function outputs
    └── sendEvent()          → Send raw protocol events

Início Rápido

import { DefaultAzureCredential } from "@azure/identity";
import { VoiceLiveClient } from "@azure/ai-voicelive";

const credential = new DefaultAzureCredential();
const endpoint = process.env.AZURE_VOICELIVE_ENDPOINT!;

// Create client and start session
const client = new VoiceLiveClient(endpoint, credential);
const session = await client.startSession("gpt-4o-mini-realtime-preview");

// Configure session
await session.updateSession({
  modalities: ["text", "audio"],
  instructions: "You are a helpful AI assistant. Respond naturally.",
  voice: {
    type: "azure-standard",
    name: "en-US-AvaNeural",
  },
  turnDetection: {
    type: "server_vad",
    threshold: 0.5,
    prefixPaddingMs: 300,
    silenceDurationMs: 500,
  },
  inputAudioFormat: "pcm16",
  outputAudioFormat: "pcm16",
});

// Subscribe to events
const subscription = session.subscribe({
  onResponseAudioDelta: async (event, context) => {
    // Handle streaming audio output
    const audioData = event.delta;
    playAudioChunk(audioData);
  },
  onResponseTextDelta: async (event, context) => {
    // Handle streaming text
    process.stdout.write(event.delta);
  },
  onInputAudioTranscriptionCompleted: async (event, context) => {
    console.log("User said:", event.transcript);
  },
});

// Send audio from microphone
function sendAudioChunk(audioBuffer: ArrayBuffer) {
  session.sendAudio(audioBuffer);
}

Configuração de Sessão

await session.updateSession({
  // Modalities
  modalities: ["audio", "text"],
  
  // System instructions
  instructions: "You are a customer service representative.",
  
  // Voice selection
  voice: {
    type: "azure-standard",  // or "azure-custom", "openai"
    name: "en-US-AvaNeural",
  },
  
  // Turn detection (VAD)
  turnDetection: {
    type: "server_vad",      // or "azure_semantic_vad"
    threshold: 0.5,
    prefixPaddingMs: 300,
    silenceDurationMs: 500,
  },
  
  // Audio formats
  inputAudioFormat: "pcm16",
  outputAudioFormat: "pcm16",
  
  // Tools (function calling)
  tools: [
    {
      type: "function",
      name: "get_weather",
      description: "Get current weather",
      parameters: {
        type: "object",
        properties: {
          location: { type: "string" }
        },
        required: ["location"]
      }
    }
  ],
  toolChoice: "auto",
});

Tratamento de Eventos (Padrão do SDK do Azure)

O SDK usa um padrão de tratamento de eventos baseado em assinatura:

const subscription = session.subscribe({
  // Ciclo de vida da conexão
  onConnected: async (args, context) => {
    console.log("Conectado:", args.connectionId);
  },
  onDisconnected: async (args, context) => {
    console.log("Desconectado:", args.code, args.reason);
  },

…