Electronic texts carry important meta-information (such as tags in HTML) that most of the current Text-to-Speech (TtS) systems ignore during the production of the speech. We propose an approach to exploit this meta-information in order to achieve a detailed auditory representation of an e-text. The e-Text to Speech and Audio (e-TSA) Composer has been designed and developed as an XML based scripting framework that can be adopted by existing TtS, with minor or major modifications. It provides a mechanism to create scripts using combined elements from e-texts and TtS systems. The e-TSA Composer can manipulate the behaviour of a TtS (e.g. the applied prosody) in order to define a finest vocalisation in response to specific e-texts.