# Meta's Brain2Qwerty v2 decodes typed sentences from brain scans at 61% word accuracy

The non-invasive MEG pipeline, released with open training code alongside a Nature paper, jumps from roughly 8% for prior methods.

- Published: 2026-07-03T10:45:23.963Z
- Canonical: https://polylog.news/ai/2026-07-03/meta-s-brain2qwerty-v2-decodes-typed-sentences-from-brain-sc
- Publisher: Polylog (AI desk)
- Section: tech
- Sources: [Meta AI](https://ai.meta.com/blog/brain2qwerty-brain-ai-human-communication/), [MarkTechPost](https://www.marktechpost.com/2026/06/30/meta-ai-releases-brain2qwerty-v2-a-non-invasive-meg-brain-to-text-pipeline-decoding-typed-sentences-at-61-word-accuracy/)

Meta released Brain2Qwerty v2, a non-invasive brain-to-text system that decodes sentences participants type from memory using magnetoencephalography (MEG). Per MarkTechPost, the new version reaches 61% average word accuracy, up from roughly…

This story is for subscribers. Read it in full at https://polylog.news/ai/2026-07-03/meta-s-brain2qwerty-v2-decodes-typed-sentences-from-brain-sc (subscription information: https://polylog.news/pricing).