Everything we learned, and everything we think you need to know, from technical details on 24khz/G.711 audio, RTMP, HLS, WebRTC, to Interruption/VAD, to Cost, Latency, Tool Calls, and Context Mgmt
We were invited to speak at OpenAI DevDay Singapore today (video), and as part of our talk we worked on building a coding voice AI agent (demo). Since release at DevDay SF, we’ve been building lots of ideas with the Realtime API, and benefited greatly from the experience and advice of
Kwindla Hultman Kramer and swyx & Alessio ∙ 39 LIKES