Ep 104: Real-time voice agents just got cheaper and more capable—OpenAI split its Realtime API into specialized models with lower latency.

Models & Agents Real-time voice agents just got cheaper and more capable—OpenAI split its Realtime API into specialized models with lower latency. What You Need to Know: OpenAI released GPT-Realtime-2.1 and a mini reasoning variant optimized for voice, cutting p95 latency by at least 25% via better caching. Tencent open-sourced Hy3, a 295B MoE with 21B active parameters and 256K context that hits 78.0 on SWE-Bench Verified. ... AI Disclosure: This podcast is curated by Patrick but uses AI-generated voice synthesis for audio production. 🎬 Watch on YouTube: https://www.youtube.com/watch?v=RYPZHgtDGVU 📝 Full show notes, transcript & sources: read the episode page 🌐 Part of the Nerra Network — explore every show at nerranetwork.com.