Build realtime multimodal agents with LiveKit and Azure | ODSP937
Livekit Azure Real Time Voice Agent Multimodal Agents Speech To Text Text To Speech Llm Integration Webrtc Azure Ai Voice Activity Detection Microsoft Build Python Agent Sdk Real Time Audio
A practical guide to building real-time voice agents using LiveKit's infrastructure combined with Azure's AI services (STT, LLM, TTS). Jesse Hall demonstrates an end-to-end implementation covering voice activity detection, low-latency audio streaming, and how to create an agent that can answer questions about Microsoft Build. Ideal for developers building production multimodal AI applications.