Abstract: A speech analysis module compares a subject text to the voice of a subject person reciting the text, and generates a personal voice library of the subject's voice. The library includes audio files of actual words spoken by the subject person, as well as morphological, syntactical and grammatical considerations affecting the pronunciation of words and pauses. Words not actually spoken by the subject can be artificially synthesized by an analysis of the subject's speech and pronunciation, and utilizing sounds and portions of words spoken by the subject. Upon request for an audio recording of an object text in the voice of the subject, an integration module retrieves discrete audio files from the personal voice library and artificially generates a voice recording of the object text in the voice of the subject. The generation and transmission of custom audio files can be part of a commercial transaction.