Neuralink's VOICE trial uses brain-to-speech with natural voice synthesis
A trial participant named Terry is training an algorithm to convert his thoughts into spoken words using his own voice.
Neuralink announced progress in its VOICE trial, a research program exploring brain-to-speech interfaces for people who cannot speak. The participant, Terry, is using his Neuralink implant to help develop and refine the technology for himself and future users.
According to Neuralink, Terry's training process began with miming speech as closely as possible, then progressed to simply thinking words while the system converts his neural signals into audio output. The synthesized speech uses his own natural voice, rather than a generic or artificial one.
The system is powered by Grok Voice, SpaceX's voice technology. Neuralink did not provide additional technical details about the trial's progress or timeline.
"Through the VOICE trial, Terry is using his Neuralink implant to help fine-tune a brain-to-voice interface for himself and others who can’t speak. He trained the algorithm first by miming speech as best he could, then by simply thinking the words and hearing them come out in his own natural voice. Powered by Grok Voice from @SpaceXAI"— X · @neuralink