Chuck Jorgensen, a scientist at the NASA Ames Research Center in Moffett Field, California, and his team are developing a machine that can translate your body's neuromuscular signals for speech, without the need to talk aloud:
We're looking at the neuromuscular patterns being sent through the nervous system and inferring from those patterns what words would have been said out loud had a person actually permitted himself to produce the acoustics.
Link - via Gizmowatch