Building Real-Time Voice Apps with OpenAI’s Realtime API

Join us for an introduction to OpenAI’s new Realtime API models and learn how to build low-latency voice, transcription, and translation experiences in under an hour.
We’ll explore the latest realtime capabilities including:

• GPT-Realtime-2 — conversational voice AI with advanced reasoning and natural speech interactions
• GPT-Realtime-Translate — live multilingual speech translation
• GPT-Realtime-Whisper — streaming speech-to-text transcription for captions, notes, and live apps

During the session we’ll cover:

• How realtime audio streaming works with WebRTC and WebSockets
• Speech-in / speech-out application patterns
• Live demos using the OpenAI Realtime API
• Best practices for latency, interruptions, and conversational UX
• Building voice agents, translators, and realtime copilots
• Common architecture patterns and deployment tips

Whether you’re building voice assistants, AI phone systems, live transcription tools, or multilingual experiences, this meetup will give you a practical starting point and example code to begin experimenting immediately.