Garianno Lorenzo and a team of programmers have developed a voice clone program that flawlessly produces original speech of a person—living or deceased—after pulling from a short voice sample. Mr. Lorenzo has worked in film and media for more than 20 years and says this new software/hardware combination will change how we conceive of the entertainment industry. He emphasizes that the program, which might be named Voice Clone or iDolly, differs from voice recognition.
Voice technologies have come a long way in the last few decades. Speech recognition has commonly been used to help people with speech disabilities or professionals who want to transcribe dictations and meetings. Voice Clone goes a step further.
Mr. Lorenzo explains that the new voice technology is able to create fully cloned, original speech that is indiscernible from the person’s real voice. This program will take whatever speech a user types in and then render the words in the authentic voice of a sampled individual.
The new technology has exciting implications for the music and film industry. Voice Clone would allow a singer to collaborate on an original song with a deceased performer or allow a deceased historical figure to make an appearance in a film under the guise of his or her real voice.
The product will launch at some point in the relatively near future.