Introducing MindSpeech
The world's first continuous thought-to-text AI model
With our new AI model MindSpeech, we have shown for the first time that AI can interpret a wide range of imagined speech directly from the brain without requiring any surgery. In other words, human participants can imagine language and sentences in their head in a natural, free-flowing and continuous manner, and the imagined language is converted directly into text.
This paves the way for advancements in how humans will communicate with technology in the future.
Signatory Statement from World-leading Experts:
“The launch of MindSpeech, the result of MindPortal’s groundbreaking AI research, marks the translation of free-form thought into text. This represents a major step forward in advancing a future where seamless communication based on brain-computer interfaces, employing the combination of non-invasive physiological measures and AI algorithms, is a reality. Previous efforts have been limited to decoding memorised words or phrases. The new approach, implemented through MindSpeech, is a significant advancement in human-AI interaction, capturing the fluid nature of internal speech. MindPortal’s AI research provides, for the first time, preliminary evidence that AI can decode continuous imagined speech from the brain.”
Professor Maysam Chamanzar
Former Lead Technical Strategist for Neuralink / Lead Scientist for DARPA N3 Neural Interface Program
Professor Gabriele Gratton
Former Lead Scientist for DARPA brain imaging program, discovered the fast optical signal (one of the highest resolution techniques in the field of non-invasive brain-imaging)
Professor Hamid Dehghani
World-leading expert in optical brain imaging, University of Birmingham
Professor Monica Fabiani
Former DARPA scientist, University of Illinois
