Sounds crazy, right? That’s because it is, and if this program ever sees a public release, it could be a serious game changer.
At this year’s Adobe MAX event showcasing the latest and greatest of the team’s ongoing projects, Project VoCo caught everyone’s attention. The project is headed by developer Zeyu Jin, and it promises to allow all the editing capabilities that photoshop provides images, to audio.
After analyzing about 20 minutes of speech from a given source, VoCo can accurately recreate the source’s voice, and configure that voice into new words and phrases that were not present in the original clip. By using a simple text box, users can add new words into the speech, seamlessly recreating a voice to edit a given clip in any number of ways.
Creative Bloq’s Craig Stewart makes a great point that the program could raise some heavy ethical concerns, but VoCo would also allow unprecedented value to media, television, and producers, who could create some wild ‘samples’ out of celebrity monologues. However, that’s all far off in the distance, as Project VoCo is still very much in research and development.
H/T: Creative Bloq | Photo: