This Groundbreaking AI Tool Converts Images Into Sound

Krotos' new AI allows users to upload a photo, generate a text prompt and see what custom audio it creates.

Have you ever seen a photograph so striking, you could almost hear the world within it? What would it sound like? Krotos has now launched AI that generates custom audio based on an uploaded image, claiming it's the "world's first" tech of its kind.

The company's Ambience Generator v2 allows users to upload a photo, including images like film stills, video screenshots or concept art. Then it uses AI to formulate a text prompt based on the image before generating custom audio to accompany it.

Krotos claims its artificial intelligence is "non-generative" and does not train itself on user-uploaded files.

"Our approach to AI is grounded in both innovation and ethical responsibility," a Krotos spokesperson told MusicTech. “When we say our AI engines are 'non-generative,' we mean they are not creating entirely new sounds from scratch. Instead, they are designed to assist sound designers by processing and enhancing existing high quality audio assets that have been recorded by professionals."

"Our commitment to ethics is reflected in how we train our AI," the statement continues. "We exclusively use professionally recorded assets that we own or have full rights to… The goal is to empower users, not replace them."

See how Krotos' Ambience Generator v2 works below.

More from Music News

LISTEN LIVE

SCHEDULE

  • Non-Stop Classic Rock

    Midnight - 8:55am

  • Tough Rock Saturday is Coming Up Next!

    8:55am - 9:00am

ON-DEMAND

NETFM CHAT ROOM