Meta's Brain2Qwerty v2 Decodes Sentences from Brain Signals in Real-Time

Meta announced Brain2Qwerty v2, the next milestone in its non-invasive brain-to-text decoder research. Building on v1, which was published in Nature, v2 is an end-to-end pipeline capable of real-time sentence decoding from raw brain signals. It advances beyond character-level performance to decoding words and semantics, achieving accuracy suitable for overall communication. The research is aimed at helping millions of people with brain lesions or disorders that prevent communication.