A system for producing audio output from interaction with printed material and a pen based computer system. The system includes a printed page including a substantially invisible position code and a human viewable image. The system further includes a pen-based computer system for determining a position of the human viewable image in response to interactions there between, e.g., based upon the pen tip's proximity to the image. The pen-based computer is operable to produce a human-audible output corresponding to the human viewable image contemporaneously with the interaction. The human viewable image may be produced independent of the pen based computer and may include a textual word and/or an image. A plurality of pages may be provided in book form allowing a plurality of audio recordings to be rendered in connection with a plurality of images, thusly providing an interactive audio book experience for the user.