skills.rest
davidrrowley
davidrrowleyCOMMUNITY
Explore all skills by this author →
Website𝕏@davidrrowleyGitHub

azure-ai-voicelive-dotnet

Enable bidirectional AI voice sessions in .NET using WebSockets and Azure authentication.

Updated Apr 12, 2026
Search Tags:#azure#real-time#dotnet#websocket#speech-to-speech#voicelive
One-click install
npx skills add https://github.com/davidrrowley/CortexYouV3 --skill azure-ai-voicelive-dotnet
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: azure-ai-voicelive-dotnet
Source: https://github.com/davidrrowley/CortexYouV3/tree/main/.agents/skills/azure-ai-voicelive-dotnet
Command: npx skills add https://github.com/davidrrowley/CortexYouV3 --skill azure-ai-voicelive-dotnet

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill removes the complexity of building low-latency, bidirectional voice interactions in .NET by documenting session lifecycle, audio streaming, authentication, and function-calling patterns for Azure Voice Live.

Core Features & Use Cases

  • Real-time bidirectional audio: Guides creating and managing VoiceLiveSession WebSocket connections to stream microphone input and receive synthesized audio responses.
  • Session configuration & turn detection: Shows how to configure modalities, voice selection, and AzureSemanticVadTurnDetection for natural conversation flow.
  • Function calling & integration: Demonstrates defining function tools, handling function call arguments, and returning function outputs within the voice session.
  • Use Case: Build a voice assistant that captures user speech, invokes backend services (for example, weather or calendar), and returns spoken answers in real time.

Quick Start

Start a VoiceLive session with DefaultAzureCredential, configure modalities for Text and Audio, stream microphone audio to the session, and handle updates to play or display responses.

Frequently Asked Questions about azure-ai-voicelive-dotnet

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I build a real-time .NET voice assistant with bidirectional audio streaming?▼

Real-time .NET voice assistants use WebSocket-based VoiceLiveSession connections to stream microphone input and receive synthesized audio. You configure session modalities for audio and text, then handle updates to play responses. This enables low-latency speech-to-speech interactions for conversational AI.

How does Azure Voice Live handle turn detection in conversational AI?▼

Azure Voice Live uses AzureSemanticVadTurnDetection for turn detection in conversational AI. This manages the session lifecycle by analyzing voice activity to determine when a user finishes speaking, allowing the voice assistant to respond naturally without requiring manual push-to-talk interactions.

Can I use function calling in a real-time .NET speech-to-speech application?▼

Function calling is supported in real-time .NET speech-to-speech applications via VoiceLiveSession. You define function tools, handle function call arguments received during the session, execute backend services like weather or calendar APIs, and return function outputs directly within the active voice session.

What authentication methods work with Azure Voice Live in a .NET application?▼

Azure Voice Live in .NET applications supports authentication options including DefaultAzureCredential. This allows you to start a VoiceLive session by passing the credential to establish secure WebSocket connections without manually managing API keys for your real-time voice assistant.

What is the best way to configure audio modalities for a .NET voice chatbot?▼

Configuring audio modalities for a .NET voice chatbot involves setting up the VoiceLiveSession to accept both Text and Audio inputs. You stream microphone audio to the session while handling updates to play or display the synthesized audio responses in real time.

Related Skills

Explore More Software Engineering Skills→
Steffen025Steffen025
186

VoiceServer

Invoke a local ElevenLabs TTS server for real-time voice notifications.

Community
Advanced
adiytharpansaadiytharpansa

sag

Convert written text into expressive speech using ElevenLabs text-to-speech.

Community
Intermediate
EmeaAppGbbEmeaAppGbb

Azure AI Projects Client Library Skill

Guide Azure AI Projects Python SDK usage for building and deploying AI applications.

Official
Advanced
microsoftmicrosoft
2.9k

azure-ai-voicelive-py

Build real-time voice AI applications in Python using the Azure Voice Live SDK.

Official
Intermediate