Prototype neural implant converts brain signals to speech in real-time

Image credit: theshubhamdhage via Unsplash

Scientists at the University of California, Davis have developed a proof-of-concept neural prosthesis that can convert brain signals into sounds almost instantly, marking an early step toward a fully digital vocal tract. Using 256 electrodes, the system records neural activity, which an AI decoder translates into speech features such as pitch and voicing. A vocoder then synthesizes these into a voice resembling the participant’s before losing speech. While not yet capable of supporting open-ended conversations, the technology demonstrates promising potential for restoring more natural communication in the future.

Source

Card NS, Wairagkar M, Iacobacci C, Hou X, Singer-Clark T, Willett FR, Kunz EM, Fan C, Nia MV, Deo DR, Srinivasan A, Choi EY, Glasser MF, Hochberg LR, Henderson JM, Shahlaie K, Brandman DM, Stavisky SD. An accurate and rapidly calibrating speech neuroprosthesis. medRxiv [Preprint]. 2024 Apr 10:2023.12.26.23300110. doi: 10.1101/2023.12.26.23300110. Update in: N Engl J Med. 2024 Aug 15;391(7):609-618. doi: 10.1056/NEJMoa2314132. PMID: 38645254; PMCID: PMC11030484.

Additional Reading

https://arstechnica.com/science/2025/06/a-neural-brain-implant-provides-near-instantaneous-speech/

https://health.ucdavis.edu/news/headlines/first-of-its-kind-technology-helps-man-with-als-speak-in-real-time/2025/06

https://www.science.org/content/article/brain-implant-lets-man-who-lost-his-speech-als-produce-natural-sounding-sentences

Previous
Previous

New nanomaterial harvests clean water from air moisture

Next
Next

The hidden dangers of visceral fat and how to manage it