Short description:

The Virtual Storyteller is a multi-agent framework for automatic story generation. It creates stories based on the actions of autonomous agents who live in a simulated story world.


Video explaining the Virtual Storyteller.

In the Virtual Storyteller, automatic story generation is carried out in two stages: Simulation (the content of the story is created by means of the multi-agent system) and Presentation (the story content is expressed in natural language and (optionally) told by a speaking embodied agent). The system architecture looks as follows:

multi agent architecture

The agents involved in the simulation stage are
  • Character Agents inhabiting the Story World and performing actions there. They have individual emotions, beliefs, and can make plans to achieve their goals.
  • World Agent responsible for keeping track of the current state of the Story World. It processes actions from the Character Agents and updates the world accordingly.
  • Plot Agent intermediating between the Character Agents and the World Agent, and creates a formal representation of the story content called the fabula. The fabula forms the basis for the next stage of story generation: presentation.
The Narrator is responsible for converting the formal content representation (the fabula) to a natural language text. Tasks include mapping story elements to sentences, combining these sentences using proper cue words ("because", "but", etc.), choosing suitable referring expressions ("Diana", "the beautiful princess", "she"), and ensuring proper morphology and word order.

The story can be presented to the user in the form of text, but it can also be actually told to the user. To this end, rules have been designed that convert standard synthesized speech to storytelling speech. Listen to the difference between the following synthetic speech samples:

Example 1 (neutral sentence): speakerstandard - storytelling style
Example 2 (suspenseful): speaker standard - storytelling style

The Interactive Storyteller

Recently an interactive version of the Virtual Storyteller has been developed. It has a graphical multi-touch interface allowing human users to control one or more characters. It has been tested in experiments with children using a multitouch table.

Interactive version of the Virtual Storyteller.


The Virtual Storyteller website, with documents and publications on different aspects of the Virtual Storyteller, can be found here:

WIKI and blog pages

Here you can find descriptions of various aspects of the Virtual Storyteller, such as the authoring process (with detailed examples):


Students interested in working on the Virtual Storyteller for a Capita Selecta, Research Topics or Masters thesis, or others who would like to know more about the Virtual Storyteller, please contact Mariët Theune.

Publications related to this showcase are:

I.M.T. Swartjes and M. Theune The Virtual Storyteller: story generation by simulation, in Proceedings of the Twentieth Belgian-Netherlands Conference on Artificial Intelligence, BNAIC 2008, University of Twente, Enschede, ISSN 1568-7805, pp. 257-264, 2008 [ BiBTeX ] [EprintsDownload PDF document
T. Alofs, M. Theune and I.M.T. Swartjes A Tabletop Board Game Interface for Multi-User Interaction with a Storytelling System, in 4th International ICST Conference on Intelligent Technologies for Interactive Entertainment (INTETAIN 2011), A.S. Camurri and C. Costa (eds), Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, volume 78, Springer Verlag, Heidelberg, ISBN 978-3-642-30213-8, ISSN 1867-8211, pp. 123-128, 2011 [ BiBTeX ] [EprintsDOI>  Download PDF document

HMI-members working on this showcase are:

Former HMI-members:

old Parlevink website   colophon   [Back] .