Azure AI Voice Live SDK for .NET. Build real-time voice AI applications with bidirectional WebSocket communication.
npx skills add https://github.com/lingxling/awesome-skills-cn --skill azure-ai-voicelive-dotnet
Real-time voice AI SDK for building bidirectional voice assistants with Azure AI.
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
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>
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)
Uri endpoint = new Uri("https://your-resource.cognitiveservices.azure.com");
AzureKeyCredential credential = new AzureKeyCredential("your-api-key");
VoiceLiveClient client = new VoiceLiveClient(endpoint, credential);
VoiceLiveClient
└── VoiceLiveSession (WebSocket connection)
├── ConfigureSessionAsync()
├── GetUpdatesAsync() → SessionUpdate events
├── AddItemAsync() → UserMessageItem, FunctionCallOutputItem
├── SendAudioAsync()
└── StartResponseAsync()
using Azure.Identity;
using Azure.AI.VoiceLive;
var endpoint = new Uri(Environment.GetEnvironmentVariable("AZURE_VOICELIVE_ENDPOINT"));
var client = new VoiceLiveClient(endpoint, new DefaultAzureCredential());
var model = "gpt-4o-mini-realtime-preview";
// Start session
using VoiceLiveSession session = await client.StartSessionAsync(model);
// Configure session
VoiceLiveSessionOptions sessionOptions = new()
{
Model = model,
Instructions = "You are a helpful AI assistant. Respond naturally.",
Voice = new AzureStandardVoice("en-US-AvaNeural"),
TurnDetection = new AzureSemanticVadTurnDetection()
{
Threshold = 0.5f,
PrefixPadding = TimeSpan.FromMilliseconds(300),
SilenceDuration = TimeSpan.FromMilliseconds(500)
},
InputAudioFormat = InputAudioFormat.Pcm16,
OutputAudioFormat = OutputAudioFormat.Pcm16
};
// Set modalities (both text and audio for voice assistants)
sessionOptions.Modalities.Clear();
sessionOptions.Modalities.Add(InteractionModality.Text);
sessionOptions.Modalities.Add(InteractionModality.Audio);
await session.ConfigureSessionAsync(sessionOptions);
await foreach (SessionUpdate serverEvent in session.GetUpdatesAsync())
{
switch (serverEvent)
{
case SessionUpdateResponseAudioDelta audioDelta:
byte[] audioData = audioDelta.Delta.ToArray();
// Play audio via NAudio or other audio library
break;
case SessionUpdateResponseTextDelta textDelta:
Console.Write(textDelta.Delta);
break;
case SessionUpdateResponseFunctionCallArgumentsDone functionCall:
// Handle function call (see Function Calling section)
break;
case SessionUpdateError error:
Console.WriteLine($"Error: {error.Error.Message}");
break;
case SessionUpdateResponseDone:
Console.WriteLine("\n--- Response complete ---");
break;
}
}
await session.AddItemAsync(new UserMessageItem("Hello, can you help me?"));
await session.StartResponseAsync();
// Define function
var weatherFunction = new VoiceLiveFunctionDefinition("get_current_weather")
{
Description = "Get the current weather for a given location",
Parameters = BinaryData.FromString("""
{
"type": "object",
"properties": {
"location": {
"type": "string",
"description": "The city and state or country"
}
},
"required": ["location"]
}
""")
};
// Add to session options
sessionOptions.Tools.Add(weatherFunction);
// Handle function call in event loop
if (serverEvent is SessionUpdateResponseFunctionCallArgumentsDone functionCall)
{
if (functionCall.Name == "get_current_weather")
{
var parameters = JsonSerializer.Deserialize<Dictionary<string, string>>(functionCall.Arguments);
string location = parameters?["location"] ?? "";
// Call external service
string weatherInfo = $"The weather in {location} is sunny, 75°F.";
// Send response
await session.AddItemAsync(new FunctionCallOutputItem(functionCall.CallId, weatherInfo));
await session.StartResponseAsync();
}
}
| Voice Type | Class | Example |
|------------|-------|---------|
| Azure Standard | AzureStandardVoice | "en-US-AvaNeural" |
| Azure HD | AzureStandardVoice | "en-US-Ava:DragonHDLatestNeural" |
| Azure Custom | AzureCustomVoice | Custom voice with endpoint ID |
| Model | Description |
|-------|-------------|
| gpt-4o-realtime-preview | GPT-4o with real-time audio |
| gpt-4o-mini-realtime-preview | Lightweight, fast interactions |
| phi4-mm-realtime | Cost-effective multimodal |
| Type | Purpose |
|------|---------|
| VoiceLiveClient | Main client for creating sessions |
| VoiceLiveSession | Active WebSocket session |
| VoiceLiveSessionOptions | Session configuration |
| AzureStandardVoice | Standard Azure voice provider |
| AzureSemanticVadTurnDetection | Voice activity detection |
| VoiceLiveFunctionDefinition | Function tool definition |
| UserMessageItem | User text message |
| FunctionCallOutputItem | Function call response |
| SessionUpdateResponseAudioDelta | Audio chunk event |
| SessionUpdateResponseTextDelta | Text chunk event |
Text and Audio for voice assistantsAzureSemanticVadTurnDetection — Provides natural conversation flowusing statement — Ensures proper session disposalif (serverEvent is SessionUpdateError error)
{
if (error.Error.Message.Contains("Cancellation failed: no active response"))
{
// Benign error, can ignore
}
else
{
Console.WriteLine($"Error: {error.Error.Message}");
}
}
InputAudioFormat.Pcm16 (16-bit PCM)OutputAudioFormat.Pcm16| SDK | Purpose | Install |
|-----|---------|---------|
| Azure.AI.VoiceLive | Real-time voice (this SDK) | dotnet add package Azure.AI.VoiceLive |
| Microsoft.CognitiveServices.Speech | Speech-to-text, text-to-speech | dotnet add package Microsoft.CognitiveServices.Speech |
| NAudio | Audio capture/playback | dotnet add package NAudio |
| Resource | URL |
|----------|-----|
| NuGet Package | https://www.nuget.org/packages/Azure.AI.VoiceLive |
| API Reference | https://learn.microsoft.com/dotnet/api/azure.ai.voicelive |
| GitHub Source | https://github.com/Azure/azure-sdk-for-net/tree/main/sdk/ai/Azure.AI.VoiceLive |
| Quickstart | https://learn.microsoft.com/azure/ai-services/speech-service/voice-live-quickstart |
This skill is applicable to execute the workflow or actions described in the overview.
Expert Mermaid diagram creation, validation, and rendering with dual-engine output (SVG/PNG/ASCII). Supports all 20+ diagram types including C4 architecture, AWS architecture-beta with service icons, flowcharts, sequence, ERD, state, class, mindmap, timeline, git graph, sankey, and more. Features code-to-diagram analysis, batch rendering, 15+ themes, and syntax validation. Use when users ask to create diagrams, visualize architecture, render mermaid files, generate ASCII diagrams, document system flows, model databases, draw AWS infrastructure, analyze code structure, or anything involving "mermaid", "diagram", "flowchart", "architecture diagram", "sequence diagram", "ERD", "C4", "ASCII diagram". Do NOT use for non-Mermaid image generation, data plotting with chart libraries, or general documentation writing.
Expert at handling file uploads and cloud storage. Covers S3, Cloudflare R2, presigned URLs, multipart uploads, and image optimization. Knows how to handle large files without blocking. Use when: file upload, S3, R2, presigned URL, multipart.
Bump the default Redis docker test image (redislabs/client-libs-test) in the shared DEFAULT_DOCKER_CONFIG and the CI matrix, then force-push the bump-test-image branch and open a PR against upstream. User-invoked only.
Bump the NVIDIA PyTorch base image (`nvcr.io/nvidia/pytorch:YY.MM-py3`) used by Megatron-LM CI. Covers the two pin sites (GitHub CI in `docker/.ngc_version.dev` and GitLab CI in `.gitlab/stages/01.build.yml`), the post-bump CI loop (re-run functional tests, refresh golden values, mark broken tests), and the gotchas that bit PRs #4611 and #4688.
Compile TensorRT-LLM on a SLURM cluster. Covers submitting a batch job with a container image, monitoring the job, and verifying the build. Use when the user wants to compile TRT-LLM remotely via SLURM rather than on a local compute node.
Updates Docker container image tags used by Aspire hosting integrations. Queries registries for newer tags, uses LLM to determine version-compatible updates, and applies changes. Use this when asked to update container image versions.
Use when a PinMe Cloudflare Worker needs R2 object storage, including secure file or image upload, streaming download, metadata lookup, deletion, listing, Range requests, or R2+D1 coordination. Guides AI to use PinMe's automatically injected env.R2 binding without R2 credentials or manual Wrangler configuration.
Analyze text and images for harmful content using Azure AI Content Safety (@azure-rest/ai-content-safety). Use when moderating user-generated content, detecting hate speech, violence, sexual content, or self-harm, or managing custom blocklists.
Take lingxling/azure-ai-voicelive-dotnet from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.