Physical Address
304 North Cardinal St.
Dorchester Center, MA 02124
Adobe’s Oriol Nieto uploaded a short video with a handful of scenes and a voice-over, but no sound effects. The AI model analyzed the video and broke it down into scenes, applying emotional tags and descriptions to each scene. Then, came the sound effects. The AI model presents a scene with an alarm clock, for example, and automatically creates a sound effect. It detected a scene where the main character (an octopus, in this case) was driving a car and added a sound effect of a door closing.
It wasn’t perfect. The alarm sounds weren’t realistic, and in a scene where two characters were hugging, the AI model added an unnatural rustling of clothes that didn’t work. Instead of manually editing, Adobe uses a Conversational interface (like ChatGPT) to describe changes. In the car scene, there was no ambient noise from the car. Instead of manually selecting the scene, Adobe uses a conversational interface and asks the AI model to add a car sound effect to the scene. It successfully found the scene, created the sound effects and placed it perfectly.
These experimental features are not available, but they usually work their way into Adobe’s suite For example, harmonizeA feature in Photoshop that automatically places assets in a scene with the correct color and lighting was shown at Sneaks last year. Now, it’s in Photoshop. Expect them to pop up by 2026.
Adobe’s announcement comes just months after video game voice actors An almost year-long strike ends To secure protections around AI—companies must obtain consent and provide disclosure agreements when game developers want to recreate a voice actor’s voice or likeness through AI. Became a singer Bracing for impact AI will be in business for a while now, and Adobe’s new features, even if they’re not creating voice-overs from scratch, Another marker of change AI is pushing the creative industries.
