YC-backed Subvocal glasses decode silent mouthing via radar at 200+ words/min
alex_verem · x · 2026-11-05
Subvocal, backed by $1.3M from YC and Afore Capital, is building glasses that use non-contact radar sensing to track speech muscles and decode nearly invisible silent mouthing into text at over 200 words per minute — enabling typing-free prompts, messages, and private conversations. Pre-orders are live, with the first batch expected to ship Q1 2027.
More from Embodied
- The CERN analogy fits robot evaluation: shared hardware, protocols and published failures — DJiafei · 2026-11-05
- Curbie robot autonomously hauls your trash bins to the curb, rain or snow — TansuYegen · 2026-11-05
- Physical AI is far from solved: benchmark numbers show robots can't plug and play yet — DJiafei · 2026-11-05
- MolmoAct 2 Takes Second to GPT-6 Astra in RoboColosseum's Real-World Robot Tests — DJiafei · 2026-11-05
- Researcher Pushes Back on RoboColosseum: Scene Breadth Won't Probe Physical Understanding — DJiafei · 2026-11-05
- Nothing teases screen-free AI-native device launching next month — The Verge AI · 2026-11-05