The MARY Text-to-Speech System

MARY is a Text-to-Speech Synthesis System for German, English and Tibetan. It was originally developed as a collaborative project of DFKI's language technology lab and the Institute of Phonetics at Saarland University and is now being maintained by DFKI.

MARY is designed to be highly modular, with a special focus on transparency and accessibility of intermediate processing steps. This makes it a suitable tool for Research and Development.

New to MARY?

First, check out the online demos:

Speech synthesis interface in Java (or the non-java online speech synthesis if you don't have Java)
EmoSpeak, a Java-based graphical interface to change the emotional tone of the voice

Want to know more about this Modular Architecture for Research on speech sYnthesis (MARY)?

Browse the Documentation section
Subscribe to the MARY users mailing list and ask questions there