: This paper presents a framework for the automatic production of Digital Talking Books (DTB). The production process converts existing audio tapes and OCR-based digitalization of text books into full-featured, multisynchronized, multimodal digital books. The framework deals with the standardization processes, media enrichment and User Interface definition. er is based on abstract, yet DTB specific, pattern-based UI specifications. This allows the definition of various forms of interaction and presentation, required by the diversity and constraints of targets users (e.g. visually impaired persons) and situations of use (e.g. learning). Balancing the focus of production between personalized, situation-based UI and adaptive ones is also considered. The article also summarizes some usability tests on generated DTBs that contributed to the refinement of the framework. Key words: UI generation, model-based tools, accessibility, user diversity