People who are not professional storytellers usually have difficulty composing travel photos and videos from a mundane slideshow into a coherent and engaging story, even when it is about their own experiences. However, consider putting the same person in a conversation with a friend - suddenly the story comes alive.

We present Raconteur 2, a system for conversational storytelling that encourages people to make coherent points, by instantiating large-scale story patterns and suggesting illustrative media. It performs natural language processing in real-time on a text chat between a storyteller and a viewer and recommends appropriate media items from a library. Each item is annotated with one or a few sentences in unrestricted English. A large commonsense knowledge base and a novel commonsense inference technique are used to identify story patterns such as problem and resolution or expectation violation. It uses a concept vector representation that goes beyond keyword matching or word co-occurrence based techniques. A small experiment shows that people find Raconteur's interaction design engaging, and suggestions helpful for real-time storytelling.