Festival is a general multi-lingual speech synthesis system developed at CSTR. It offers a full text to speech system with various APIs, as well an environment for development and research of speech synthesis techniques. It is written in C++ with a Scheme-based command interpreter for general control.
Release Notes: This release improves support for modern compilers. There are assorted bugfixes.
Release Notes: An HTS hidden markov model based synthesis engine from the Nagoya Institute of Technology. A Multisyn general purpose unit selection synthesis engine from CSTR. Support for GCC 3.2 and 3.3, and Intel 8.0. clunits unit selection improvements. Apple OS X support. Many bugfixes.
Release Notes: This release offers minor bug fixes and new compiler support.
Release Notes: Various changes (see the ChangeLog), and now released under a free license.
Release Notes: Many small but important bug fixes, new KAL US male voice, Improved KED by power normalization, updated lexicons with missing entries found over large corpora. New LTS models for US and UK English.