Neuralink VOICE trial. Credit: Neuralink
Neuralink showed a new VOICE trial update on September 18 featuring participant Terry, who is using his brain implant to help train a thought-to-speech system so he and others who cannot speak can talk again in a reconstructed natural voice.
According to the company, Terry first trained the algorithm by miming speech as best he could, then progressed to simply thinking the words and hearing them spoken aloud in his own voice. Neuralink said the pipeline is powered by Grok Voice from SpaceXAI.
The clip sits in the same investigational VOICE lane as this week’s earlier milestone with participant Kenneth Shock, who was shown producing an audible “I love you” from neural signals alone. Telepathy work still focuses on cursor and device control. VOICE is about decoding intended speech for people with ALS or similar conditions.
Neuralink has not published Terry’s implant date, clinical metrics, vocabulary size, latency figures, or how many VOICE participants are active in this round. The system remains investigational and is not cleared as a general consumer product.
Even so, the September 18 post makes the stack clearer: a Neuralink implant feeding intended speech, with SpaceXAI’s Grok Voice handling the spoken output in a voice meant to sound like the user’s own.
Want to see more of our stories on Google?
P.S. — Buying a new Tesla? Click here to save $1,000 USD, while supporting independent news.
Help support us by shopping on Amazon here.
Links in this post are affiliate links, so we earn a tiny commission at no charge to you. Thanks for supporting independent media!
