Adobe’s Project VoCo Could Change How We Edit Audio

Meet Project VoCo, Adobe’s new audio editing software that allows you edit speech the same way Photoshop allows you to edit images.

All images via Adobe Max

This year’s Adobe Max brought out some big name speakers and some pretty cool sneak looks at what’s in store for the Creative Cloud. From team projects to social sharing, Adobe is certainty pushing the envelope in terms of what their programs can do for the everyday video editor. But is audio the next frontier?

At the “Sneak Peeks” portion of the conference this year, Adobe introduced Project Voco, an audio voice editing software that promises to give Photoshop-like controls to audio and speech. Here’s what you need to know.

Updated Speech Pattern and Tone Recognition

The Adobe Max demo presents an Adobe team member working with audio taken by celebrity host Jordan Peele and gives a glimpse into the potential of the project. From the sound heard from the stage, the audio, when moved around and created (more on that below), actually sounds like it’s coming from the original source. It has close to the same cadence, pace, voice and tone. For video editors, this is, of course, obviously huge. It could help save hours of scouring and editing to try and find or change VO audio.

New Sentence Text Editing Technology

While the technology isn’t exactly new, it does sound like it’s working at a higher level than your third-party extensions. The ability to copy, paste, and move around text in single words or blocks is very much a useful feature that could make audio editing easier. However, this appears to be with audio only, so for video editors, it will be most useful when working with voice-over projects.

Experimental Unique Word and Sentence Creation

Burying the lead here a little bit, but the standout technological advancement in Project VoCo is the program’s ability to create new words and short sentences in the project that analyses and copies the speakers voice. This is HUGE, obviously. It allows video editors the ability to instantly cover mistakes, make changes, make updates, or even create speech that simply never existed before.

The project is still a work-in-progress. At its core, VoCo’s main focus intends to be on audio-only projects such as podcasts and audio books. To really get enough data to create new words and sentences, the program needs about 20 minutes of source audio to analyze. However, it does open doors for possible video-editing implications in the future. Having edited interview and VO for hours on end before, the potential to replace painstaking audio scrubbing with simply typing in what you want your subject to say is too good to ignore.

Here’s the full presentation from Adobe Max’s Sneak Peeks. Keep your eye on Project VoCo as more updates are expected in early 2017.

What do you think about the future of audio editing? Let us know in the comments.