EA's SEED lab built a machine learning system that can take a single base sound effect and automatically generate many realistic variations of it — for example, the same explosion at different distances or intensities. This acts as a tool for game sound designers to speed up audio production.

The method uses a type of generative AI model called WaveFlow and was presented at the AAAI Conference on AI and Interactive Digital Entertainment (AIIDE) in 2022. The system uses mel spectrograms as control inputs, letting designers tune the output's characteristics. A patent for the technology (US 12,420,192) was granted to EA on September 23, 2025, credited to inventors Monica Villanueva Aylagas, Albin Jansson, and Sergi Andreu. The tool is intended for internal use by sound designers across EA's game studios.