azure-ai-voicelive-ts

import { DefaultAzureCredential, ManagedIdentityCredential } from "@azure/identity";
import { VoiceLiveClient } from "@azure/ai-voicelive";
 
// Local dev: DefaultAzureCredential. Production: set AZURE_TOKEN_CREDENTIALS=prod or AZURE_TOKEN_CREDENTIALS=<specific_credential>
const credential = new DefaultAzureCredential({requiredEnvVars: ["AZURE_TOKEN_CREDENTIALS"]});
// Or use a specific credential directly in production:
// See https://learn.microsoft.com/javascript/api/overview/azure/identity-readme?view=azure-node-latest#credential-classes
// const credential = new ManagedIdentityCredential();
const endpoint = "https://your-resource.cognitiveservices.azure.com";
 
const client = new VoiceLiveClient(endpoint, credential);

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);

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

import { DefaultAzureCredential } from "@azure/identity";
import { VoiceLiveClient } from "@azure/ai-voicelive";
 
const credential = new DefaultAzureCredential({requiredEnvVars: ["AZURE_TOKEN_CREDENTIALS"]});
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);
}

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",
});

const subscription = session.subscribe({
  // Connection lifecycle
  onConnected: async (args, context) => {
    console.log("Connected:", args.connectionId);
  },
  onDisconnected: async (args, context) => {
    console.log("Disconnected:", args.code, args.reason);
  },
  onError: async (args, context) => {
    console.error("Error:", args.error.message);
  },
  
  // Session events
  onSessionCreated: async (event, context) => {
    console.log("Session created:", context.sessionId);
  },
  onSessionUpdated: async (event, context) => {
    console.log("Session updated");
  },
  
  // Audio input events (VAD)
  onInputAudioBufferSpeechStarted: async (event, context) => {
    console.log("Speech started at:", event.audioStartMs);
  },
  onInputAudioBufferSpeechStopped: async (event, context) => {
    console.log("Speech stopped at:", event.audioEndMs);
  },
  
  // Transcription events
  onConversationItemInputAudioTranscriptionCompleted: async (event, context) => {
    console.log("User said:", event.transcript);
  },
  onConversationItemInputAudioTranscriptionDelta: async (event, context) => {
    process.stdout.write(event.delta);
  },
  
  // Response events
  onResponseCreated: async (event, context) => {
    console.log("Response started");
  },
  onResponseDone: async (event, context) => {
    console.log("Response complete");
  },
  
  // Streaming text
  onResponseTextDelta: async (event, context) => {
    process.stdout.write(event.delta);
  },
  onResponseTextDone: async (event, context) => {
    console.log("\n--- Text complete ---");
  },
  
  // Streaming audio
  onResponseAudioDelta: async (event, context) => {
    const audioData = event.delta;
    playAudioChunk(audioData);
  },
  onResponseAudioDone: async (event, context) => {
    console.log("Audio complete");
  },
  
  // Audio transcript (what assistant said)
  onResponseAudioTranscriptDelta: async (event, context) => {
    process.stdout.write(event.delta);
  },
  
  // Function calling
  onResponseFunctionCallArgumentsDone: async (event, context) => {
    if (event.name === "get_weather") {
      const args = JSON.parse(event.arguments);
      const result = await getWeather(args.location);
      
      await session.addConversationItem({
        type: "function_call_output",
        callId: event.callId,
        output: JSON.stringify(result),
      });
      
      await session.sendEvent({ type: "response.create" });
    }
  },
  
  // Catch-all for debugging
  onServerEvent: async (event, context) => {
    console.log("Event:", event.type);
  },
});
 
// Clean up when done
await subscription.close();

// Define tools in session config
await session.updateSession({
  modalities: ["audio", "text"],
  instructions: "Help users with weather information.",
  tools: [
    {
      type: "function",
      name: "get_weather",
      description: "Get current weather for a location",
      parameters: {
        type: "object",
        properties: {
          location: {
            type: "string",
            description: "City and state or country",
          },
        },
        required: ["location"],
      },
    },
  ],
  toolChoice: "auto",
});
 
// Handle function calls
const subscription = session.subscribe({
  onResponseFunctionCallArgumentsDone: async (event, context) => {
    if (event.name === "get_weather") {
      const args = JSON.parse(event.arguments);
      const weatherData = await fetchWeather(args.location);
      
      // Send function result
      await session.addConversationItem({
        type: "function_call_output",
        callId: event.callId,
        output: JSON.stringify(weatherData),
      });
      
      // Trigger response generation
      await session.sendEvent({ type: "response.create" });
    }
  },
});

// Server VAD (default)
turnDetection: {
  type: "server_vad",
  threshold: 0.5,
  prefixPaddingMs: 300,
  silenceDurationMs: 500,
}
 
// Azure Semantic VAD (smarter detection)
turnDetection: {
  type: "azure_semantic_vad",
}
 
// Azure Semantic VAD (English optimized)
turnDetection: {
  type: "azure_semantic_vad_en",
}
 
// Azure Semantic VAD (Multilingual)
turnDetection: {
  type: "azure_semantic_vad_multilingual",
}

import {
  VoiceLiveError,
  VoiceLiveConnectionError,
  VoiceLiveAuthenticationError,
  VoiceLiveProtocolError,
} from "@azure/ai-voicelive";
 
const subscription = session.subscribe({
  onError: async (args, context) => {
    const { error } = args;
    
    if (error instanceof VoiceLiveConnectionError) {
      console.error("Connection error:", error.message);
    } else if (error instanceof VoiceLiveAuthenticationError) {
      console.error("Auth error:", error.message);
    } else if (error instanceof VoiceLiveProtocolError) {
      console.error("Protocol error:", error.message);
    }
  },
  
  onServerError: async (event, context) => {
    console.error("Server error:", event.error?.message);
  },
});

import { setLogLevel } from "@azure/logger";
 
// Enable verbose logging
setLogLevel("info");
 
// Or via environment variable
// AZURE_LOG_LEVEL=info

// Browser requires bundler (Vite, webpack, etc.)
import { VoiceLiveClient } from "@azure/ai-voicelive";
import { InteractiveBrowserCredential } from "@azure/identity";
 
// Use browser-compatible credential
const credential = new InteractiveBrowserCredential({
  clientId: "your-client-id",
  tenantId: "your-tenant-id",
});
 
const client = new VoiceLiveClient(endpoint, credential);
 
// Request microphone access
const stream = await navigator.mediaDevices.getUserMedia({ audio: true });
const audioContext = new AudioContext({ sampleRate: 24000 });
 
// Process audio and send to session
// ... (see samples for full implementation)