Edinburgh, Scotland (January 9, 2025)—Software developer Krotos has unveiled an update to its AI Ambience Generator v2 for Krotos Studio that enables creators to generate audio ambiences directly from an image.
During 2024, Krotos introduced AI Ambience Generator v1, a text-based tool that allowed users to describe a scene and quickly receive a unique ambience preset. Building on that foundation, AI Ambience Generator v2 takes it a step further.
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 bring the scene to life. By providing an image—which can be a film still, a video screenshot or concept art—AI generates a custom prompt. Users can refine this prompt, and Krotos Studio produces a tailored preset, transforming visuals into sound.
Krotos Debuts Creator Toolkit
Key features include image-to-sound functionality. Upload an image to generate a scene-specific audio prompt, streamlining the process from visuals to sound. The AI-generated prompt can be customized for mood, complexity and energy level of the soundscape.
The app includes a 2.6GB AI Ambience Expansion Pack focused on urban environments, providing more creative possibilities, and works within DAWs, NLEs, or as a standalone too. Multi-channel outputs allow detailed control over sound elements, while preset export makes sharing and reuse simple.
