Krotos have announced that the Ambience Generator v2 found in their powerful Krotos Studio software has been updated with a AI-powered new image-to-sound function. The new feature, which is said to be the first commercially available tool of its kind, allows creators to generate audio ambiences directly from an image, eliminating the need to sift through extensive sample libraries in search of their desired sounds.
The Ambience Generator v2 feature, which was introduced in 2024, makes it possible for users to create new soundscapes based on a text prompt, offering a quick and easy way to generate unique ambience sounds that suit their project. Now, the company have taken things a step further by including a tool that uses an imported image — such as a picture, video screenshot or a project’s concept art — rather than a text description.
Key features
- Image-to-Sound Functionality: Upload an image to generate a scene-specific audio prompt.
- Editable Prompts: Refine the AI-generated prompt to customise the mood, complexity and energy level of the resulting soundscape.
- Content Expansion: Includes a 2.6GB AI Ambience Expansion Pack focused on urban environments.
- Seamless Integration: Works effortlessly within DAWs and NLEs, or as a standalone application.
- Advanced Control and Sharing: Multi-channel outputs allow detailed control over sound elements, while preset export makes sharing and reuse simple.
More information about the AI Ambience Generator v2 and Krotos Studio can be found on the company’s website.
