A computer-implemented method to create a cinematic storytelling experience is provided. The method includes receiving, from a client device, a user selection of a story, and obtaining, from a server, (i) a lexicon associated with the selected story, the lexicon comprising a limited number of keywords, and (ii) instructions associated with the selected story, the instructions including instructions to perform at least one action responsive to the client device detecting a keyword. The method further includes receiving user input to initiate verbal recitation of the selected story, detecting correspondence between the verbal recitation and at least one of the keywords, and performing the at least one action according to the instructions for the at least one keyword.