This paper presents a method for an automatic compilation of a phonologically rich text database, which is used in a concatenative text-to-speech (TTS) synthesis system. In this method, linguistic features are predicted from text using Festival's linguistic engine. A set of phonological units for a specific text is compiled from attribute value lists (AVLs). Phrases/sentences that contain the phonological units that are not included in the database are added to the database. This is an efficient way for generating database prompts with a specific prosodic content; the prompts can then be recorded and converted into voice. The method described here can be used for languages other than English.