Subvocal Smart Glasses Convert Silent Mouth Movements Into Digital Text
New wearable tech uses radio waves to enable silent computer interaction and dictation.
1Silent Speech Interface Innovation
Subvocal is developing smart glasses that translate silent mouth movements into text. By capturing subtle facial muscle changes, the device allows users to communicate with computers without speaking aloud. This technology aims to replace traditional keyboards and voice commands, offering a discreet method for typing emails, messages, or code in public.
2Radio Wave Sensing Mechanism
The hardware utilizes low-powered radio waves projected toward the wearer’s face. These waves are distorted by muscle movements and facial shape changes during speech. The system processes these distortions to decode open-ended speech at speeds exceeding 200 words per minute, maintaining a low error rate despite the small initial training dataset.
3Development and Engineering Pivot
Founders Aarush Yadav and Arnav Kumar began the project at a hackathon using EMG electrodes attached to the face. They later pivoted to RF sensing to create a more viable commercial product. Overcoming significant engineering challenges, they developed a low-noise RF stack and optimized antenna placement to ensure maximum signal field overlap.
4Calibration and AI Training
The system employs pre-trained AI models to minimize user setup time. During testing, YC partner Dave Lieb successfully calibrated the headset to his specific speech patterns by reading only 20 sentences. This rapid calibration process is essential for the product's usability, allowing the device to adapt quickly to different individual articulation styles.
5Prototype Evolution and Design
The current demo headset is a 3D-printed prototype, which the company acknowledges is not yet fashionable. Future versions are expected to be significantly sleeker, as indicated by current website mockups. The transition from a table full of electronics and taped antennas to a semi-portable board represents the team's rapid four-month development progress.
6Funding and Market Entry
Backed by Y Combinator and Afore Capital, the startup is moving toward a commercial release. Preorders are currently open at an early bird price of $499, with a $199 deposit required upfront. The remaining $300 balance is due when the glasses ship, which is currently scheduled for the first quarter of 2027.
7Unresolved Technical Specifications
While the proof of concept confirms the existence of decodable signals, several key details remain undisclosed. The company has not yet finalized specifications regarding battery life, total accuracy rates, or potential mobile application integration. These missing metrics are critical for determining the device's long-term viability and performance in real-world professional work environments.
8Future of Silent Productivity
Subvocal envisions silent speech becoming a primary interface for human-computer interaction. By enabling high-speed input without auditory disturbance, the technology could transform productivity for professionals across various industries. Whether the startup can successfully scale this hardware remains to be seen, but the initial results demonstrate a potential shift in wearable computing.