Mezzo is an AI (Artificial Intelligence) system designed and programmed by Daniel Brown for his Doctoral Dissertation in at the University of California at Santa Cruz (June 2012).  It composes neo-Romantic game soundtracks in real time.  These soundtracks are adaptive: the music changes based on what characters in the game are doing and experiencing.  These actions and experiences are transformed into musical aspects based on theories of musical expression and semiotics in Classical and Romantic music put forth by several theorists and musicologists: Agawu, Grabócz, Caplin, Hatten, Almén.

The following is a brief demo video of the program running.  For more information (a lot more), please see Daniel's doctoral dissertation.