|
This is the secondary US mirror site hosted by the CMU speech group for Edinburgh University's Festival Speech Synthesis System The primary distribution site is http://festvox.org/festival
Festival offers a general framework for building speech synthesis systems as well as including examples of various modules. As a whole it offers full text to speech through a number APIs: from shell level, though a Scheme command interpreter, as a C++ library, and an Emacs interface. Festival is multi-lingual (currently English, Welsh and Spanish) though English is the most advanced.
Festival version 1.4.3 is available under a free for any use licence as described here.
Unlike the rest of the distribution whose use is basically unrestricted, note that the lexicon for British English voices is based on Oxford Advanced Learners' Dictionary of Current English festlex_OALD.tar.gz is free only for non-commercial use. The American voices (kal and ked) and the US English lexicon does not have such a restriction
See the README-1.4.3-RELEASE for a description of the files in the distribution and the dependencies between them.4 American voices and Mexican Spanish are now available with a new signal processing module from the TTS groups at CSLU at Oregon Graduate Institute. http://cslu.cse.ogi.edu/tts/download
To run Festival you need:
Please direct any questions to Alan W Black