Meta Announces Brain2Qwerty v2, Real-Time Brain-to-Text Decoder Advancing to Word and Semantic Level

Meta shared Brain2Qwerty v2, the next milestone in non-invasive brain-to-text decoding. Building on v1 published in Nature, v2 is the highest-performing end-to-end pipeline for real-time sentence decoding from raw brain signals. It advances beyond character-level to decoding words and semantics, enabling accurate overall communication. Meta believes this research can help millions with brain lesions or disorders that prevent communication.