The MARY Text-to-Speech System
NOTE: This website is no longer updated and will be replaced soon by the one currently at http://lnv-90208.sb.dfki.de/
MARY is an open-source, multilingual Text-to-Speech Synthesis platform written in Java. 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.As of version 5.0, MARY TTS supports German, British and American English, Telugu, Turkish, Russian and Italian; more languages are in preparation. MARY TTS comes with toolkits for quickly adding support for new languages and for building unit selection and HMM-based synthesis voices.
New to MARY?
First, check out the online demo:
- Speech synthesis interface directly in your web browser
Want to know more about this Modular Architecture for Research on speech sYnthesis (MARY)?