Adobe has unveiled a new tool that allows creators to change the emotions of a voice-over in real-time. The company calls it 'Corrective AI' and claims it can alter the tone, style, and even the overall attitude of a pre-recorded audio track with just a few clicks.
The technology uses artificial intelligence to analyze an existing audio file and adjust its parameters to achieve a specific emotional response, such as moving from one voice to another or altering the volume and inflection of a voice.
In a demo, Adobe showed how this feature can be used to extract different parts of a single audio track, creating multiple versions with different effects. For example, if you were recording in a public place where licensed music was playing in the background, the AI model could separate the music, replace it with a similar track from Adobe Stock and apply effects to give it the ambiance of the original.
These new features leverage artificial intelligence to fix day-to-day problems for video editors and creators. The features will first appear at Adobe's MAX Sneaks showcase before being integrated into the full suite later on.
The technology uses artificial intelligence to analyze an existing audio file and adjust its parameters to achieve a specific emotional response, such as moving from one voice to another or altering the volume and inflection of a voice.
In a demo, Adobe showed how this feature can be used to extract different parts of a single audio track, creating multiple versions with different effects. For example, if you were recording in a public place where licensed music was playing in the background, the AI model could separate the music, replace it with a similar track from Adobe Stock and apply effects to give it the ambiance of the original.
These new features leverage artificial intelligence to fix day-to-day problems for video editors and creators. The features will first appear at Adobe's MAX Sneaks showcase before being integrated into the full suite later on.
. As a content creator, I've had my fair share of audio mishaps and it can be so frustrating when you're stuck with an embarrassing mistake. Being able to tweak emotions in real-time would give me the freedom to experiment without having to start from scratch every time.
. I mean, think about it - with Corrective AI, you could be like, "Hey, make my intro sound more energetic and motivational" or "Tone down the sarcasm in this segment". The possibilities are endless! And the fact that Adobe is making these features available at MAX Sneaks means we can get our hands on them sooner rather than later 
. Can't wait to dive into the world of Corrective AI! 
. and the possibilities are endless, like taking a video shot in a crowded place and then easily removing the background noise or music without having to do any manual editing 
. adobe is killing it with this tech update! 
can't wait for it to become available to everyone 
. The idea of being able to separate background noise and replace it with something better is genius 
, imagine using this on podcasts or interviews where background chatter is distracting 
. And that demo where they showed how to create multiple versions of a track in seconds? Mind blown 
! It's like having a superpower for video editing 
. Can't wait to try it out and see what I can do with it 
And don't even get me started on how this could be used to manipulate audio for nefarious purposes... 
It sounds like Adobe is trying to solve a problem that doesn't really exist... or at least not one that needs solving. 