Use Case
Azure Ai Voicelive Py is a powerful AI agent skill that extends your assistant with new capabilities. Build real-time voice AI applications using Azure AI Voice Live SDK (azure-ai-voicelive). Use this skill when creating Python applications that need real-time bidirectional audio communication with Azure AI, including voice assistants, voice-enabled chatbots, real-time speech-to-speech translation, voice-driven avatars, or any WebSocket-based audio streaming with AI models. Supports Server VAD (Voice Activity Detection), turn-based conversation, function calling, MCP tools, avatar integration, and transcription. This guide walks you through installing Azure Ai Voicelive Py, configuring it for your setup, and running your first commands β so you can start getting value in minutes.
Install Azure Ai Voicelive Py: npx clawhub@latest --dir ~/.claude/skills install azure-ai-voicelive-py
Restart your AI client (Claude Code, Cursor, Gemini CLI, or OpenClaw)
Type a natural language request related to design & creative to trigger Azure Ai Voicelive Py
Review the output and refine your prompt for better results
Combine Azure Ai Voicelive Py with other skills to build multi-step workflows
Copy these prompts and use them with your AI agent after installing Azure Ai Voicelive Py
Help me get started with Azure Ai Voicelive Py
What can Azure Ai Voicelive Py do for my design & creative workflow?
Show me an example of using Azure Ai Voicelive Py
Select your agent
Option 1: Install via CLI (recommended)
Recommended (no pre-install needed)
npx clawhub@latest --dir ~/.claude/skills install azure-ai-voicelive-pyOr via clawhub CLI (if already installed)
clawhub --dir ~/.claude/skills install azure-ai-voicelive-pyβ οΈ Requires Node.js 18+. No Node? Use Option 2 below to download the ZIP instead. Install Node.js β
Option 2: Manual install (no Node required)
Download the ZIP, extract it, and place the folder at the path below. Restart your agent to activate.
Install path
~/.claude/skills/azure-ai-voicelive-py/π‘Extract and place the folder at the path above, then restart your agent.