Get ready for a whole new universe of scams and conspiracy theories. At its annual MAX event, Adobe showed off a tool it’s working on that’s basically Photoshop for audio, in that it can generate authentic-sounding speech in anyone’s voice based on a small sample.
You read that right: Feed Project VoCo about 20 minutes of audio featuring someone’s voice, and the software will then let you edit that speech to deliver natural results. You can cut and paste words, and even add words that weren’t even part of the original sample file.
Hear it in action in this video clip from the event, which features comedian Jordan Peele freaking out exactly the same way I did when I saw this:
The Verge noted that Project VoCo is currently in the works and is being built by members of Adobe Research and folks from Princeton University. The company explained the software’s functionality in a statement:
When recording voiceovers, dialog, and narration, people would often like to change or insert a word or a few words due to either a mistake they made or simply because they would like to change part of the narrative. We have developed a technology called Project VoCo in which you can simply type in the word or words that you would like to change or insert into the voiceover. The algorithm does the rest and makes it sound like the original speaker said those words.
Is it too late to rename it to Project Loco?
The 💜 of EU tech
The latest rumblings from the EU tech scene, a story from our wise ol' founder Boris, and some questionable AI art. It's free, every week, in your inbox. Sign up now!
Expect to hear a lot of claims of the use of doctored audio from politicians and sleazebags in the coming years. Thanks, Adobe.
Get the TNW newsletter
Get the most important tech news in your inbox each week.