University of Twente Student Theses
AI GM : creating a speech to speech AI to play Dungeons and Dragons with
Hassing, Matt (2025) AI GM : creating a speech to speech AI to play Dungeons and Dragons with.
|
PDF
5MB |
| Abstract: | Tabletop role-playing games often rely on human Game Masters to manage complex narratives and mechanics, but with artificial intelligence, human game masters could be helped and, in some cases, not even needed anymore. This project explores how artificial intelligence can address these challenges by automating game master responsibilities through a speech-to-speech conversational system. Leveraging a large language model for narrative generation, combined with speech recognition, text-to-speech, and a custom electronic 20-sided die. We developed an artificial intelligence game master that is capable of real-time interactions and has integrated dice throws through the electronic 20 sided die. Informed through iterative design and backed by a user experience study with a score of 83 on the system usability scale, this prototype demonstrated strong engagement, particularly for novice players. This work underscores the potential of artificial intelligence to enhance table top role playing and other board games through adaptive, immersive, and accessible gameplay. |
| Item Type: | Essay (Bachelor) |
| Faculty: | EEMCS: Electrical Engineering, Mathematics and Computer Science |
| Subject: | 54 computer science, 76 recreation, leisure |
| Programme: | Creative Technology BSc (50447) |
| Link to this item: | https://purl.utwente.nl/essays/105422 |
| Export this item as: | BibTeX EndNote HTML Citation Reference Manager |
Show download statistics for this publication
Show download statistics for this publicationRepository Staff Only: item control page