Voice ordering demo renders UI mid-sentence with ~200ms from word to screen
schwentker · x · 2026-11-11
A developer built a voice coffee-ordering system with typesafeai's Jev, demoing UI manipulation at the speed of thought: the drink and any updates appear on screen while the user is still mid-sentence, roughly 200ms from spoken word to display.
Boosters see this kind of low-latency, real-time voice-to-UI response as a glimpse of why voice interfaces could become huge.
Related event: Developer demos 200ms voice coffee ordering with Jev(2 posts)→
More from coding & agent
- Claude agent drives a real Leica microscope via MCP, autofocus and all — jwt0625 · 2026-11-11
- Yacine's agent talk: context moves outside the model, harnesses self-edit — yacinelearning · 2026-11-11
- UluP Nexus: a read-only MCP server for discovering indie software with verified submissions — Potential-Art7696 · 2026-11-11
- Cursor ships multiplayer in Projects: shared task board with agent-to-agent requests — mattyp · 2026-11-11
- Why agents will soon have only one tool: Code Mode cuts spend 15%, +3.5 Terminal-Bench points — dl_weekly · 2026-11-11
- MCP Stock Assistant serves real-time A-share and US stock data via Xueqiu API — modelcontextprotocol · 2026-11-11