This skill provides specialized implementation guidance for the Azure AI Voice Live Python SDK, enabling developers to build low-latency, conversational voice applications. It covers essential patterns for managing bidirectional WebSocket connections, handling real-time audio streams, and configuring advanced session parameters like Voice Activity Detection (VAD). By integrating this skill, Claude can effectively assist in building interactive AI phone agents, virtual assistants, and accessibility tools that utilize the GPT-4o-realtime-preview model for seamless human-AI speech interaction.
主な機能
01Real-time bidirectional WebSocket communication for ultra-low latency.
02Comprehensive audio stream management for PCM16 and G.711 formats.
03Sophisticated turn detection using Azure Semantic VAD.
04Integrated function calling support within voice conversational flows.
0561 GitHub stars
06Dynamic session configuration for voice profiles and modalities.
ユースケース
01Creating interactive AI voice assistants and customer support bots.
02Developing real-time speech-to-speech translation tools.
03Building voice-controlled business logic with complex back-end function execution.