On Sept. 14, 2026, Paradromics, a neurotechnology company developing a high-data-rate brain-computer interface (BCI) platform designed to restore and enhance human capabilities, announced that the first participant implanted with the Connexus^® BCI has successfully used the system for real-time speech and text communication. The milestone was achieved as part of the Connect-One Early Feasibility Study, conducted under an FDA-approved Investigational Device Exemption (IDE). Moving beyond researcher-selected copy tasks, the participant chose her own words, answered open-ended questions, and communicated with her grandchildren during a live phone call. The demonstration establishes a real-time communication loop in which neural activity associated with speech is decoded into language and returned to the participant as text and synthesized speech.

Data from the first participant also show that Paradromics has identified distinct patterns of neural activity associated with both attempted speech, when a person tries to produce speech, and imagined speech, when a person internally generates language without physically attempting to speak. These findings demonstrate a path toward restoring communication while providing a broader view of the neural information accessible through high-resolution intracortical recording.

“When we implanted Connexus in June, we crossed the threshold into long-term human use. We have now crossed another: our first participant is choosing her own words and using neural activity to communicate them in real time,” said Matt Angle, PhD, founder and CEO of Paradromics. “She determines what she wants to say, and the system enables her to say it.”

The first participant is a Michigan woman in her 60s living with a progressive motor neuron disease that has significantly affected her ability to speak. Motor neuron diseases are a group of neurological disorders that affect voluntary movement and can impair speech, mobility, and other motor functions; they include conditions such as amyotrophic lateral sclerosis (ALS) and primary lateral sclerosis (PLS). She has severe dysarthria and retains limited speech, and while her husband can often understand her, communicating with others has become far more challenging.

When the system was activated for free speech, she chose a sentence that captured both her experience and the purpose of the study: “Okay, I have a lot to say.” The sentence was generated by the participant and decoded in real time exactly as she intended, with no errors. Later, Matthew Willsey, MD, PhD, a University of Michigan Health neurosurgeon and Connect-One investigator, asked what she would say to a participant considering a BCI and this surgery. Through Connexus, she responded: “Don’t be afraid. It’s a wonderful experience to be able to help others by your participation in the research study.” The decoded output matched every intended word.

During the same session, the participant used the Connexus BCI to communicate with family members during a live phone call. She asked her grandchildren questions and responded using speech generated by the system.

The Connexus BCI is designed to record neural activity at the resolution of individual neurons and transmit that information wirelessly through intact skin to the external computing system. Paradromics researchers are examining how neural activity changes as the participant listens to language, prepares to speak, attempts speech, and generates language internally. The data collected to date show that speech-related information can be identified across hundreds of neural recording channels and represented as distinct patterns that change depending on the task being performed.