The Subvocal Company (YC F26) is building a wearable that lets you communicate with computers without speaking out loud.

Our goal is to turn deliberate subvocal speech, words you form internally without producing an audible voice or overt movement, into text and commands. Imagine writing an email, coding, searching the web, or talking to an AI at the speed of speech while sitting in a quiet office, on a train, or in the middle of a meeting, without anyone around you hearing a word or seeing you do anything.

Making this work requires solving an unusually difficult sensing and machine learning problem. The broader technical design space includes RF sensing, EMG, EEG, mmWave, and other non-invasive physiological sensing methods. For competitive and IP reasons, we are not publicly disclosing the exact architecture of our current system yet. What we can say is that we have already built prototypes that decode continuous subvocal speech at 200+ words per minute with high accuracy from real physiological signals, and we are now turning that research into a portable device that can work across people after a short calibration.

We are a small team in San Francisco, backed by Y Combinator and Afore Capital, along with some incredible angels. We move extremely quickly, build most things from first principles, and work across sensing, machine learning, embedded systems, hardware, and product design. The people joining now will not be optimizing a mature product or working on one narrow subsystem. They will help make foundational technical decisions, own entire areas of the company, and shape what this interface ultimately becomes.

We think silent speech will become a new fundamental way humans interact with computers. If working on something that still sounds slightly like science fiction, but is rapidly becoming a real engineering problem, sounds exciting to you, we would love to hear from you.