Sonancia is a multi-faceted generator for digital horror games, capable of generating levels and their soundscapes, based on a designer or machine defined progression of tension called the Tension Frame (see Fig.1). This frame allows designers to define how many rooms are going to be in the main path of the level (X-Axis) and how tense each room should be (Y-Axis), where a higher and lower values dictate either a rise or fall in tension, respectively.

Tension Frame

Fig.1: The Tension Frame for a level.

Levels consist of a haunted dungeon divided by multiple rooms, where players are tasked to find the old statue (i.e. the objective). Sonancia generates levels using genetic algorithms and the progression of tension defined by the designer, which guides how lights, monsters and audio triggers are placed in the level. The system generates both the level layouts, which include the placement of lights and enemy monsters; and a soundscape, which consists of placing 3D audio triggers within the level and background audio. The current version of the Sonancia system can be downloaded here .

The following videos show gameplay footage of Sonancia:


  • P. Lopes, A. Liapis and G. N. Yannakakis, “Framing Tension for Game Generation,” in Proceedings of the Seventh International Conference on Computational Creativity, 2016. [pdf]
  • P. Lopes, A. Liapis, and G. N. Yannakakis, “Targeting Horror via Level and Soundscape Generation,” in Proceedings of the AAAI Artificial Intelligence for Interactive Digital Entertainment Conference, 2015. [pdf]
  • P. Lopes, A. Liapis, and G. N. Yannakakis, “Sonancia: Sonification of Procedurally Generated Game Levels,” in Proceedings of the ICCC workshop on Computational Creativity & Games, 2015. [pdf]

Sonancia Crowdsourcing DataSet

This DataSet includes the crowdsourcing annotations and the features extracted from the openSMILE tool, which was used to train audio affect models for the Sonancia system. If you end up using this dataset within your work, please cite the following paper: Lopes, Liapis and Yannakakis, “Modelling Affect for Horror Soundscapes”, IEEE Transactions of Affective Computing, 2017.