This graduation thesis explored how large language models (LLMs) can enable new forms of tangible storytelling. Through hands-on prototyping and testing, I created a series of interactive prototypes of AI-enabled tangible storytelling systems and gathered users' experience when telling stories with it. I developed a conceptual framework to guide and evaluate the design of these storytelling systems. Synthesizing the findings from user tests and the conceptual framework, I developed a refined demo as the final outcome. The demo provided valuable insights on design opportunities and challenges, sparking multiple future directions. Together, these insights form a toolkit for designers who want to combine AI and tangible interactions in storytelling. LLM-driven artifacts have the power to enable creative, embodied, and social narratives, opening doors to new ways of defining and developing stories.