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.
Initial release – enables building real-time voice AI apps using Azure AI Voice Live SDK for Python. - Real-time bidirectional WebSocket audio streaming with Azure AI models. - Supports Server VAD, turn-based conversation, function calls, tools, transcription, and avatar integration. - Easy authentication via `DefaultAzureCredential` or API key. - Provides structured resources for session, response, audio buffers, and conversation state. - Includes example snippets for session config, event handling, audio streaming, and interrupt management. - Supports voice selection, multiple audio formats, and manual or VAD turn-taking.