Meta's brain-scanning system reads sentences non-invasively, code open source
Meta has released the code for Brain2Qwerty v2, a non-invasive system that uses AI to decode brain activity into text. The system achieves 61% word accuracy by analyzing magnetoencephalography data, aiming to assist individuals with communication-impairing brain lesions.
Why it matters
This technology represents a significant advancement in non-surgical neuroprosthetics, potentially offering a scalable communication solution for patients without the risks of invasive brain surgery.
Research From Brain Waves to Words: Brain2Qwerty Offers a New Path to Communication Without Surgery June 29, 2026 • 3 minute read Last year, we introduced Brain2Qwerty v1, research that uses AI to decode brain activity into text without any surgical implant. Now we're sharing the next step: Brain2Qwerty v2, the highest-performing end-to-end pipeline capable of real-time sentence decoding from non-invasive brain recordings, approaching levels of accuracy previously exclusive to techniques that require brain surgery.
The report focuses on technical research and open-source contributions from a major tech company.
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in