Automatic generation of documentary content

摘要

Embodiments are directed towards generating an interactive target document based on a static source document. The source document may be a textbook. An interactive, animated, multi-dimensional, and/or multi-layered target document is generated that documents the source document. The target document may include accompanying audio that includes speech in virtually any natural language, independent of the native language of the source document. The target document may be a presentation document (e.g. a slide deck), a video document (e.g. a movie), a report, a desktop application, a mobile application, a word processing document, a web page, an e-book, a spreadsheet, or the like. The target document may be generated automatically to document, expand upon, and provide a greater context and interpretation of the contents of the source document (i.e. the source document contents or simply the source contents). Thus, the target document may be a documentary of the source document.