MaryTTS 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.
It is now maintained by the Multimodal Speech Processing Group in the Cluster of Excellence MMCI and DFKI.
As of version 5.2, MaryTTS supports German, British and American English, French, Italian, Luxembourgish, Russian, Swedish, Telugu, and Turkish; more languages are in preparation.
MaryTTS comes with toolkits for quickly adding support for new languages and for building unit selection and HMM-based synthesis voices.
First, check out the online demo:
Want to know more about this Modular Architecture for Research on speech sYnthesis (MARY)?