GoKawiilYC-backed startup Subvocal builds smart glasses that transcribe silent, unspoken speech
The Subvocal Company, a Y Combinator F26 startup founded by Georgia Tech students Aarush and Arnav, has built prototype smart glasses that use radio-frequency sensing to decode silent or mouthed speech into text in real time. The founders say the device works even without visible lip movement, after earlier attempts using EMG facial electrodes proved unreliable due to sweat, interference and placement issues.
GoKawiil's interpretation of the reporting above, not reported fact.
If the RF-based approach proves robust outside demos, it could enable private, hands-free dictation in settings like offices or libraries where speaking aloud to AI tools is impractical. The shift away from invasive EMG electrodes toward a wearable glasses form factor suggests the founders are prioritizing everyday usability, though questions about accuracy, privacy and comfort at scale remain untested publicly.
- Subvocal glasses use RF signals to decode silent or unmouthed speech into text.
- The startup pivoted from an EMG electrode prototype built at a hackathon to RF sensing for practicality.
- Subvocal is part of Y Combinator's F26 batch, founded by two former Georgia Tech CS students.
Source: news.ycombinator.com, 2026-11-02
Published there as: “Show HN: Subvocal – Talk to your computer without making noise”
Read the original report → The summary and analysis above are GoKawiil's own, written from reporting by the source above. Facts and quotes belong to the original publisher.