This Beanie is designed to read your mind

Speech-to-text capability is now baked in everything modern computers. But what if you didn’t have to dictate to your computer? What if you could only type by thinking?

Silicon Valley startup Sabi is emerging from obscurity with that goal. The company is working on a brain portable which decodes a person’s internal speech into words on a computer screen. CEO Rahul Chhabra says its first product, a brain-reading beanie, will be available by the end of the year. The company also designs a baseball cap version.

The technology is known as a brain-computer interfaceor BCI, a device that provides a direct communication path between the brain and an external device. While many companies like Elon Musk’s Neuralink is developing surgically implanted BCIs for people with severe motor disabilities, Sabi’s device could allow anyone to become a cyborg.

It’s not exactly Musk’s vision of the future, which involves implanted brain chips to enable humans to merge with AI. But venture capitalist Vinod Khosla, who was an early investor in OpenAI, says a non-invasive, wearable device is the only way to get many people to use BCI technology.

“The biggest and worst application of BCI is if you can talk to your computer by thinking about it,” says Khosla, founder of Khosla Ventures, one of Sabi’s investors. “If you’re going to have a billion people using BCI every day to access their computers, it can’t be invasive.”

Sabi’s brain-reading hat relies on EEG, or electroencephalography, which uses metal discs placed on the scalp to record the brain’s electrical activity. Decoding imagined speech from EEG is already possible, but it is currently limited to small sets of words or commands rather than continuous, natural speech.

Sensors line the inside of the cap and read brain signals non-invasively.Photo: Courtesy of Sabi

The downside of a wearable system is that the sensors have to listen to the brain through a layer of skin and bone, which dampens neural signals. Surgically implanted devices pick up much stronger signals because they sit so close to neurons. Sabi thinks the way to increase accuracy with a wearable device is to greatly scale up the number of sensors in his device. Most EEG devices have a dozen to several hundred sensors. Sabi’s cap will have anywhere from 70,000 to 100,000 miniature sensors.

“Given that high-density observation, it determines exactly what and where neural activity is occurring. We use that information to get much more reliable data to decode what a person is thinking,” says Chhabra.

The company aims for an initial typing speed of around 30 words per minute. It’s slower than most people type, but he says the speed will improve as users spend more time with the cap.