Building Real-Time Voice Agents with OpenAI's Agent SDK

Build a real‑time voice agent with LiveKit WebRTC and OpenAI’s Realtime API, using JavaScript function calls and memory to create a digital barista.

Overview

Live coding demonstration showing how to build real-time voice conversations with AI using LiveKit’s WebRTC infrastructure and OpenAI’s Realtime API. I’ll walk through the actual Javascript code to create a multimodal agent with function calling.
Then I’ll add memory capabilities to create a “Digital Barista” that remembers customer preferences across sessions.

Links

Tech stack

Finding related talks...