azure-ai-voicelive-dotnet

name	azure-ai-voicelive-dotnet
description	Azure AI Voice Live SDK for .NET. Build real-time voice AI applications with bidirectional WebSocket communication.
type	skill
created	2026-02-27T00:00:00.000Z
domain	cloud-infrastructure
category	azure
risk	unknown
source	community
tags	["skill","cloud-infrastructure","azure","voicelive"]

Azure.AI.VoiceLive (.NET)

Real-time voice AI SDK for building bidirectional voice assistants with Azure AI.

Installation

dotnet add package Azure.AI.VoiceLive
dotnet add package Azure.Identity
dotnet add package NAudio                    # For audio capture/playback

Current Versions: Stable v1.0.0, Preview v1.1.0-beta.1

Environment Variables

AZURE_VOICELIVE_ENDPOINT=https://<resource>.services.ai.azure.com/
AZURE_VOICELIVE_MODEL=gpt-4o-realtime-preview
AZURE_VOICELIVE_VOICE=en-US-AvaNeural
# Optional: API key if not using Entra ID
AZURE_VOICELIVE_API_KEY=<your-api-key>

Authentication

Microsoft Entra ID (Recommended)

using Azure.Identity;
using Azure.AI.VoiceLive;

Uri endpoint = new Uri("https://your-resource.cognitiveservices.azure.com");
DefaultAzureCredential credential = new DefaultAzureCredential();
VoiceLiveClient client = new VoiceLiveClient(endpoint, credential);

Required Role: Cognitive Services User (assign in Azure Portal → Access control)

API Key

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

Client Hierarchy

VoiceLiveClient
└── VoiceLiveSession (WebSocket connection)
    ├── ConfigureSessionAsync()
    ├── GetUpdatesAsync() → SessionUpdate events
    ├── AddItemAsync() → UserMessageItem, FunctionCallOutputItem
    ├── SendAudioAsync()
    └── StartResponseAsync()

Core Workflow

1. Start Session and Configure

using Azure.Identity;
using Azure.AI.VoiceLive;

var endpoint = new Uri(Environment.GetEnvironmentVariable("AZURE_VOICELIVE_ENDPOINT"));
 client =  VoiceLiveClient(endpoint,  DefaultAzureCredential());

 model = ;


 VoiceLiveSession session =  client.StartSessionAsync(model);


VoiceLiveSessionOptions sessionOptions = ()
{
    Model = model,
    Instructions = ,
    Voice =  AzureStandardVoice(),
    TurnDetection =  AzureSemanticVadTurnDetection()
    {
        Threshold = ,
        PrefixPadding = TimeSpan.FromMilliseconds(),
        SilenceDuration = TimeSpan.FromMilliseconds()
    },
    InputAudioFormat = InputAudioFormat.Pcm16,
    OutputAudioFormat = OutputAudioFormat.Pcm16
};


sessionOptions.Modalities.Clear();
sessionOptions.Modalities.Add(InteractionModality.Text);
sessionOptions.Modalities.Add(InteractionModality.Audio);

 session.ConfigureSessionAsync(sessionOptions);