SnapSound: Empowering everyone to customize sound experience with Generative AI

The rise of user-centric experiences in the digital landscape has led to a surge in demand for personalized multimedia content. Users now seek to customize not only visual but also auditory components to suit their preferences. In this context, sound design plays a crucial role, enabling users to tailor audio experiences accordingly. However, its inherent complexity poses various challenges, particularly for non-expert users. To address this challenge, we introduce SnapSound, a novel assistive system designed specifically for non-experts in sound design for video content. Our system leverages generative AI to streamline the sound design process and offers intuitive tools for sound selection, synchronization, and seamless integration with visuals. Through a user study, we evaluate SnapSound's usability and effectiveness compared to manual editing. Furthermore, our study provides valuable insights and design recommendations for enhancing user experience of future AI-based sound design systems. This work represents a significant step forward in empowering non-experts to easily customize their auditory experiences.