Dev claims the best voice mode and computer use he's used, built on OpenAI Realtime 2 and Claude
RileyRalmuto · x · 2026-11-13
Developer Riley Ralmuto says he has built the best voice mode and computer use experience he has ever used.
- The stack: OpenAI Realtime 2 for voice, computer use powered by Claude (and "Jev"), both planned to ship inside his app.
- He stresses it's not the try-hard kind of realism — no fake breathing or hums, and not duplex — it's just clean and good.
- Key improvement: the model knows when to stay silent after you finish speaking, instead of feeling obligated to respond. His main complaint now is having to prompt it "so what do you think?" — a much better problem to have.
More from Models
- ChatGPT Dot Appears to Be Rolling Out in EU, Pro User Reports Access — kimmonismus · 2026-11-13
- Why AI Slop Is So Frustrating to Read: Hidden Subjects and Buried Actions — teortaxesTex · 2026-11-13
- MSR: Rewriting fewer than 10 dormant neurons backdoors any LLM agent, no training needed — mikeflache · 2026-11-13
- Google's Logan Kilpatrick asks users what to ship next; community wants a new Gemma — jacek2023 · 2026-11-13
- Microsoft diagnostic AI solves 83% of NEJM cases vs 36% for physicians — realmeetjames · 2026-11-13
- Opus 5.5 generates a full Blender 3D model in seconds, wows game developer — Scobleizer · 2026-11-13