Until now, every person who utilized the technology has had the same voice — which sounds deep and computerized. But thanks to VocaliD, that’s changing.
“You see a 3-year-old girl using that voice, and then you see a 40-year-old male using that voice, and it’s odd. It can’t really be an extension of the individual if someone else has that same voice,” Rupal Patel, associate professor at Northeastern University and the developer behind VocaliD told The Huffington Post. “That was when we first started thinking: ‘Isn’t there a way to make these voices more personalized?”
Patel uses technology to blend a person’s unique speech with a healthy speaker’s voice to create a sound that is “understandable but unique to the person that we want to build it for.”