FreeTTS is a speech synthesis system written entirely in the JavaTM programming language. It is based upon Flite: a small run-time speech synthesis engine developed at Carnegie Mellon University. Flite is derived from the Festival Speech Synthesis System from the University of Edinburgh and the FestVox project from Carnegie Mellon University.
It supports AU and WAV formats in 16/8k. It has been tested on the Solaris TM Operating Environment, Mac OS X, Linux and Win32 operating systems.
This release of FreeTTS includes:
- Core speech synthesis engine
- Support for a number of voices:
- an 8khz diphone, male, US English voice
- a 16khz diphone, male US English voice
- a 16khz limited domain, male US English voice
- Support for importing voices from FestVox (US English only)
- Specific support for importing CMU ARCTIC voices from FestVox (US English only)
- Support for MBROLA voices (downloaded separately):
- a 16khz female, US English voice
- two 16khz male US English voices
- Partial support for JSAPI 1.0
- Extensive API documentation
- Several demo applications