In a major breakthrough for assistive technology, researchers at Stanford University have developed a brain-computer interface (BCI) capable of decoding imagined speech — the internal, silent words people think — and translating them into spoken language.
The advancement could dramatically improve communication for individuals with severe paralysis who have lost the ability to speak.
Unlike earlier BCIs that relied on brain signals from attempted movements of the mouth or vocal cords, the Stanford team focused specifically on decoding inner speech, also known as silent self-talk.
Lead author Erin Kunz explained that “this is the first time they’ve managed to understand what brain activity looks like when you just think about speaking, emphasizing the potential for more natural communication for those with motor impairments.”

Read: Dubai’s path to global healthcare leadership
A major step forward in brain-computer communication
The study involved four participants living with paralysis due to ALS (amyotrophic lateral sclerosis) or brainstem stroke.
Researchers implanted microelectrode arrays in the motor cortex — the area of the brain responsible for speech movements.
Participants were instructed to either try to vocalize words or simply imagine saying them. Using advanced AI models, the team was able to decode the brain’s neural activity related to phonemes (the smallest units of speech) and reconstruct them into full sentences.
Despite the weaker neural signals associated with imagined speech, the BCI achieved up to 74 percent real-time accuracy in word recognition —highlighting the technology’s significant potential.
To ensure user privacy, the researchers also developed a “thought password” system. This safety feature activates decoding only when a specific phrase is silently imagined, preventing unintended translation of thoughts.
The system worked 98 percent of the time, offering a reliable safeguard and keeping control firmly in the hands of users.
The Stanford team’s innovation marks a major step forward in brain-computer communication and offers renewed hope for people who are otherwise locked in by paralysis.