Over several weeks a neural network has been trained to match faces and audio. With a training batch of tens of thousands of frames the network has learned to construct a human face from any given audio input. With a mixture of House, Glitchpop and Schneckno robinrabauke interactively explores the work of tschänz in a audiovisual performance. The two artists are experimenting with questions, answers and the neural network participates in a dialogue about faces, machines, music and a new reality that connects the perceptions of one world, seen by different minds.