Recently, we explored and trained different state-of-the-art text-to-speech (TTS) architectures for Catalan. We used existing datasets but also produced a new Catalan multi-accent dataset to train these architectures. The objective of our work is to improve the quality of current TTS systems in Catalan and export the resulting models for potential interactive applications and video games. For this reason, our set of multi-speaker and multi-accent Catalan TTS models are presented within a demo made in Unity. The users are able to interact with game characters which are attached to our Catalan TTS. While generated Catalan speech replies are reproduced, execution time, real-time factor and transcription are shown on screen. Exported weights, such as data and demo source code, are released to the public.