A peripheral device, such as a controller or wearable device, receives information about the states of the digital environment from the system. The device allows the user to enter information and collects data on the immediate physical environment to inform narrative choices. The multimodal peripheral device provides text-to-speech and speech-to-text capabilities and monitors narrative adherence in real-time. The peripheral device also enables the transmission of media types, ambience-related elements, and map responsibilities and roles to specific agents in a multi-agent system.