|
npx skills add https://github.com/microsoft/skills --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/ # Required: Voice Live endpoint
AZURE_VOICELIVE_MODEL=gpt-4o-realtime-preview # Required: model deployment name
AZURE_VOICELIVE_VOICE=en-US-AvaNeural # Optional: Voice Live voice name
AZURE_VOICELIVE_API_KEY=<your-api-key> # Only required for AzureKeyCredential auth
AZURE_TOKEN_CREDENTIALS=prod # Required only if DefaultAzureCredential is used in production
using Azure.Identity;
using Azure.AI.VoiceLive;
Uri endpoint = new Uri("https://your-resource.cognitiveservices.azure.com");
// Local dev: DefaultAzureCredential. Production: set AZURE_TOKEN_CREDENTIALS=prod or AZURE_TOKEN_CREDENTIALS=<specific_credential>
var credential = new DefaultAzureCredential(
DefaultAzureCredential.DefaultEnvironmentVariableName
);
// Or use a specific credential directly in production:
// See https://learn.microsoft.com/dotnet/api/overview/azure/identity-readme?view=azure-dotnet#credential-classes
// var credential = new ManagedIdentityCredential();
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 should be used when working with LaminDB, an open-source data framework for biology that makes data queryable, traceable, reproducible, and FAIR. Use when managing biological datasets (scRNA-seq, spatial, flow cytometry, etc.), tracking computational workflows, curating and validating data with biological ontologies, building data lakehouses, or ensuring data lineage and reproducibility in biological research. Covers data management, annotation, ontologies (genes, cell types, diseases, tissues), schema validation, integrations with workflow managers (Nextflow, Snakemake) and MLOps platforms (W&B, MLflow), and deployment strategies.
Latch platform for bioinformatics workflows. Build pipelines with Latch SDK, @workflow/@task decorators, deploy serverless workflows, LatchFile/LatchDir, Nextflow/Snakemake integration.
Run Python code in the cloud with serverless containers, GPUs, and autoscaling. Use when deploying ML models, running batch processing jobs, scheduling compute-intensive tasks, or serving APIs that require GPU acceleration or dynamic scaling.
Comprehensive healthcare AI toolkit for developing, testing, and deploying machine learning models with clinical data. This skill should be used when working with electronic health records (EHR), clinical prediction tasks (mortality, readmission, drug recommendation), medical coding systems (ICD, NDC, ATC), physiological signals (EEG, ECG), healthcare datasets (MIMIC-III/IV, eICU, OMOP), or implementing deep learning models for healthcare applications (RETAIN, SafeDrug, Transformer, GNN).
Advanced GitHub Actions workflow automation with AI swarm coordination, intelligent CI/CD pipelines, and comprehensive repository management
This skill should be used when working with LaminDB, an open-source data framework for biology that makes data queryable, traceable, reproducible, and FAIR. Use when managing biological datasets (scRNA-seq, spatial, flow cytometry, etc.), tracking computational workflows, curating and validating data with biological ontologies, building data lakehouses, or ensuring data lineage and reproducibility in biological research. Covers data management, annotation, ontologies (genes, cell types, diseases, tissues), schema validation, integrations with workflow managers (Nextflow, Snakemake) and MLOps platforms (W&B, MLflow), and deployment strategies.
Build end-to-end MLOps pipelines from data preparation through model training, validation, and production deployment. Use when creating ML pipelines, implementing MLOps practices, or automating model training and deployment workflows.
Comprehensive healthcare AI toolkit for developing, testing, and deploying machine learning models with clinical data. This skill should be used when working with electronic health records (EHR), clinical prediction tasks (mortality, readmission, drug recommendation), medical coding systems (ICD, NDC, ATC), physiological signals (EEG, ECG), healthcare datasets (MIMIC-III/IV, eICU, OMOP), or implementing deep learning models for healthcare applications (RETAIN, SafeDrug, Transformer, GNN).
Take microsoft/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.