Adobe can now “Photoshop” voices with VoCo
The recording industry has often had to overdub voices in film and on radio and audio tracks. Perhaps the original just wasn’t good enough, or the client wanted a word added, or it didn’t sound right the first time. Until now, you’d have to have the voiceover artist dub it in again, sometimes at a considerable cost and extra time.
With Adobe’s new Project VoCo, one can now just type in a word and it will automatically be said by whomever did the original recording. It’s essentially “Photoshopping” voiceovers.
Adobe demoed the new technology at its MAX conference. At the conference, Adobe’s Zeyu Jin demoed the technology, which was developed with Princeton University, for the first time.
“You guys have been making weird things online with photo editing,” said Jin. “We’ll do the next thing today. Let’s do something to human speech. Like changing what you said in your wedding.”
The demo took the conference’s co-host, actor/comedian Jordan Peele’s voice as a sample. In it, he said “I kissed my dogs and my wife.” The text of his VO came up under the wavelength. As Jin changed the text to read “I kissed my wife and my dogs.” Aside from an audible blip (which can be smoothed out by an engineer) it sounded like Peele actually said it that way. But the editor doesn’t even have to have the words that were actually said to be able to fabricate a new phrase. Jin then typed in “I kissed Jordan and my dogs.” The realistic sound of the word wowed Peele enough so he jumped out of his seat in amazement.
This voice manipulating software is still in the demo phase, but #VoCo could revolutionize the way editors work with voiceover artists.
Jin went on to say that there are “watermarks” in place so that listeners can authenticate what was actually said and so the software is not used for nefarious purposes, which is necessary, because unlike Photoshop, which you still have to have skill to use, VoCo can be used by anyone who knows how to type. It’s a brave new world out there, and one that’s getting easier to use constantly.
Despite the excitement around the product, some feel that this treads the line on privacy.
"It seems that Adobe's programmers were swept along with the excitement of creating something as innovative as a voice manipulator, and ignored the ethical dilemmas brought up by its potential misuse," said Dr. Eddy Borges Rey, a lecturer in media and technology at the University of Stirling in Scotland to the BBC. "Inadvertently, in its quest to create software to manipulate digital media, Adobe has [already] drastically changed the way we engage with evidential material such as photographs.
"This makes it hard for lawyers, journalists, and other professionals who use digital media as evidence."