Project VoCo is the Photoshop for audio that will soon have you worrying about what you didn’t say. According to Adobe, the new editing suite will let you add almost perfect words to an audio track with consideration to the original speaker’s tone and speaking pattern.
The project is currently under development and Adobe Research wing is working with Princeton University to get the core algorithms right. As of such, we don’t yet have a time to delivery. All we know is it has the ability to add words that didn’t exist in an audio file in the first place.
Project VoCo will be an innovation audio editor that goes beyond your standard speech editing and noise cancellation. The algorithm can apparently generate new words from recorded audio.
This new product from Adobe will understand the hallmarks of the person’s speech and replicate it. All you need is at least 20 minutes of recorded speech from the person before it can do the replication. Adobe managed to showcase a near perfection word addition to a piece of audio with what we can call near-perfection.
Adobe’s official statement believes that this will change the voiceover and narration market. “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.” All you have to do is type the words you want and the software will take care of the rest.
If this makes it to the market, this will be as powerful as Photoshop has been in the photo editing and image creation world. This will definitely transform how sound engineers edit their products hence rooting out unnecessary reruns in the recording booth.
What worries me most, however, is the ethical implications Project VoCo might have on the society. Photoshop has already taught us to doubt every image we see. Audio will soon join that list if what Adobe promises of Project VoCo is true.