Skills
.Work. You
Rest

voice-live

Community

Build real-time voice agents with Azure Voice Live

Software Engineering#text-to-speech#real-time#WebSocket#Azure#speech-to-text#voice-live
Authorpascalvanderheiden
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill enables developers to create real-time voice-enabled agents by connecting to Azure Voice Live via WebSocket, providing low-latency audio streaming, speech-to-text, text-to-speech, avatars, and tool integration.

Core Features & Use Cases

  • Real-time bidirectional audio with WebSocket for seamless conversations across languages.
  • Broad STT/TTS capabilities (140+ locales for STT and 600+ voices across locales) and avatar integration for engaging user experiences.
  • Function calling (VoiceRAG) and tool integration to perform live actions, queries, and knowledge access.
  • Session management, turn detection, noise suppression, and echo cancellation to ensure natural, robust interactions.
  • Use Cases: build voice assistants, customer support bots, voice-enabled tutorials, and hands-free workflows.

Quick Start

Prerequisites: Azure Voice Live resource, Python 3.9+, authentication via Entra ID or API key.

Installation: pip install -r requirements.txt

Run minimally: export AZURE_SPEECH_RESOURCE_NAME=your-resource-name python examples/minimal_example.py

Dependency Matrix

Required Modules

websocketsazure-identitypyaudio

Components

scriptsreferences

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: voice-live
Download link: https://github.com/pascalvanderheiden/my-agent-skills/archive/main.zip#voice-live

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 223,000+ vetted skills library on demand.