Startup Sabi is developing a hat that reads thoughts and turns them into text

A hat that reads minds — sounds like science fiction, but that's exactly what California-based startup Sabi promises. The company is developing a wearable device in the form of a regular knitted beanie, equipped with sensors that read electrical activity in the brain and convert it to text in real time. If the technology works as intended, it's one of the first real steps toward what researchers and journalists have long called the cyborg era — when the boundary between human and machine begins to blur not in an operating room, but right in your closet.

Brain-computer interfaces have existed for several decades already. But so far they remain the domain of clinics, military laboratories, and narrowly specialized medical devices. The main reason is complexity and invasiveness: the most accurate BCI systems require surgical implantation of electrodes directly into the cerebral cortex.

This is the path Neuralink is taking, and the first clinical results are indeed impressive — paralyzed patients controlled computers through thought alone. But you can't build a mass market on surgical implants. Sabi is betting on the opposite approach: a completely non-invasive interface built into a piece of clothing that you put on in the morning like any other item.

The device is based on electroencephalography. EEG sensors embedded in the beanie pick up weak electrical signals that the brain generates at the moment a person intends to speak a word or mentally imagines a speech movement — what's called imagined speech. These signals are processed by machine learning algorithms that recognize characteristic patterns and decode the user's intention.

The result — text appearing on the screen without a single keystroke and without a word spoken aloud. The key technical problem of non-invasive EEG devices is the signal-to-noise ratio. Brain signals picked up from the scalp are roughly a thousand times weaker than signals from implanted electrodes and are easily masked by artifacts: muscle movement, blinking, external electromagnetic interference.

This is why most attempts to create a thought reader in the form of a consumer headset or beanie have yielded limited results — devices only worked with a narrow set of commands or required hours of individual calibration. A breakthrough is only possible with more powerful algorithms, and this is where modern neural networks are opening new possibilities. Sabi has not yet disclosed the technical details of its algorithms or specific accuracy metrics.

This is typical for early-stage startups: it's more important to attract attention and investment than to answer tough technical questions. Wired describes the development as a device capable of opening a door to a cybernetic future — phrasing that is so far closer to marketing narrative than verified fact. Nevertheless, the direction is strategically important.

The wearable neurointerface industry is experiencing obvious growth: Meta is investing in speech reading via EMG bracelets, Emotiv and Neurosity sell EEG headsets for developers, OpenBCI is building an open ecosystem for neurohackers. The fundamental difference in Sabi's approach is its focus on the mass consumer with a product that doesn't look like medical or tech equipment. Just a hat.

Nothing extra on the outside. If the company manages to achieve acceptable accuracy and reliability in real-world conditions, the consequences will be significant. First and foremost — for people with speech disorders and motor disorders: Parkinson's disease, amyotrophic lateral sclerosis, stroke consequences.

For them, an accessible non-invasive brain-computer interface could be a fundamentally new way to communicate with the world. The next audience is the productivity market: text input through imagined speech is theoretically faster than any keyboard. For now, Sabi is a bet on technology that hasn't yet proven itself in mass application.

But these are exactly the kinds of bets — on non-invasiveness, consumer form factor, and consumer scale — that distinguish the next wave of neurotech from the previous one. A hat that reads minds is becoming ever closer to reality.