By Stephen Schneck

Ever since mobile devices started getting smaller than a laptop, engineers have been tackling the difficult question of how we’re supposed to enter text. We’ve gone from tiny physical keyboards, to touchscreen keyboards, to gesture-based glide typing. On wearables, the situation’s even trickier, and it can feel like we’re stuck either using voice input or left awkwardly poking in the air at a virtual keyboard. But now one startup has a clever, hands-free solution that works silently.

How many of you speak aloud to yourself as you type? Or maybe when proofreading, do you ever silently mouth the words as you’re reading them? You might be a prime candidate for trying out Subvocal’s glasses tech, which translates silent mouth movements into written text.

Rather than pointing cameras at your face or anything like that, Subvocal instead relies on radio signals to work out what you’re “saying.” The tech is based on AlterEgo from the MIT Media Lab. While that approach measured muscle impulses with electrodes, Subvocal beams a radio signal into your head that’s modulated as the muscles in your mouth move — sort of like radar.

We’ve seen a lot of different approaches to smart glasses, ranging from lightweight audio-based models to ones with high-res built-in displays. Subvocal’s solution hardly even sounds like it counts as “smart” glasses at all, and really feels more like an unusual input peripheral — like a magic Bluetooth keyboard we wear on our face. And indeed, despite how fantastical the tech seems, it actually does appear to work — and work well.