One way researchers are trying to restore the ability to speak for those who have lost — or never had — the capability is by translating neural signals into sounds and sentences. In other words, if you think of what you want to say, a program will spit it out for you.
Boston University's Speech Lab has been at it for a few years now, working with a mute and paralyzed volunteer who agreed to a brain implant. For most of the year, Speech Lab has been working on replicating sounds, such as vowels, as a stepping stone to more complex words and sentences:
In our initial studies, the volunteer typically failed to produce the vowel consistently in his first five attempts, but by the sixth attempt his ability to control the synthesizer had improved to the point where he was successful on most subsequent attempts.
Check out the video above to see one of BU's tests (you may want to have your sound down a little bit as "the synthesizer is quite loud, at the volunteer's request").