Krotos launches the “world’s first” commercial AI image-to-sound featureKrotos has launched the “world’s first” commercial AI image-to-sound feature, available now within its Krotos Studio software.
The AI-powered Ambience Generator v2 lets users upload a picture, from which Krotos’s AI will generate a custom text prompt. The prompt is then used to create tailored audio ambiences, which can then be refined by adjusting the prompt and editing the sounds created.

READ MORE: Azealia Banks is obsessed with Teenage Engineering and the OP-XY: “They’re really s**tting on every audio hardware company out there. Nobody is this cool”

Krotos introduced AI Ambience Generator v1 last year, a text-based tool that allowed users to describe a scene and quickly receive a unique ambience preset. Now for version two, users can provide images such as a film still, a video screenshot, or concept art for the AI to work its magic.
Users working with AI-generated videos often need to add their own sounds to silent visuals, and now they can take a still from their video and quickly bring the scene to life with “precision and ease”. The Ambience Generator v2 works within DAWs, NLEs, or as a standalone tool.
For a clearer idea on how it sounds, check out the video below:

Krotos states that its AI is not generative. To get a bit more context on how it works, MusicTech reached out to Krotos directly: “Our approach to AI is grounded in both innovation and ethical responsibility,” a spokesperson told us. “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.
“This ensures that the creative control remains firmly in the hands of the user and the quality of the sound is always high unlike the results of the existing generative models. Our commitment to ethics is reflected in how we train our AI. We exclusively use professionally recorded assets that we own or have full rights to… The goal is to empower users, not replace them.”

Krotos also confirms that it regularly adds new sounds to Krotos Studio on a monthly basis, to ensure users “continue to receive ongoing value and access to fresh, high-quality content”.
The AI Ambience Generator is available in both Krotos Studio and Krotos Studio Pro. Currently with the Pro version, you can add your own sounds after the software generates an ambience, allowing you to further customise the result to fit your project.
Looking ahead, the brand is planning an update that will allow the generator to create entirely new ambiences directly using sounds from your personal library. This may cause some alarm bells about the possibility of AI being able to train itself on the files that users import, but Krotos says this is not the case.
It explains, “The AI Ambience Generator does not and will not train itself on the files that users import. We prioritise user privacy and ethical AI practices, so any audio files you add are used solely for creating your own custom ambiences. These files remain entirely under your control and are not incorporated into our broader system or models.”
To find out more about the AI Ambience Generator or explore plans for its Studio software, head over to Krotos.
The post Krotos launches the “world’s first” commercial AI image-to-sound feature appeared first on MusicTech.