 | This articleneeds additional citations forverification. Please helpimprove this article byadding citations to reliable sources. Unsourced material may be challenged and removed. Find sources: "Festival Speech Synthesis System" – news ·newspapers ·books ·scholar ·JSTOR(February 2013) (Learn how and when to remove this message) |
| Festival | |
|---|---|
| Developer | Centre for Speech Technology Research (CSTR) of theUniversity of Edinburgh |
| Stable release | 2.5 / December 2017; 7 years ago (2017-12) |
| Written in | C++ |
| Operating system | Cross-platform |
| Type | Speech synthesizer |
| License | Similar toMIT License (Free software) |
| Website | www |
TheFestival Speech Synthesis System is a general multi-lingualspeech synthesis system originally developed byAlan W. Black, Paul Taylor and Richard Caley[1] at the Centre for Speech Technology Research (CSTR) at theUniversity of Edinburgh. Substantial contributions have also been provided byCarnegie Mellon University and other sites. It is distributed under afree software license similar to theBSD License.
It offers a fulltext to speech system with variousAPIs, as well as an environment for development and research of speech synthesis techniques. It is written inC++ with aScheme-likecommand interpreter for general customization and extension.[2]
Festival is designed to support multiple languages, and comes with support forEnglish (British andAmerican pronunciation),Welsh, andSpanish. Voice packages exist for several other languages, such asCastilian Spanish,Czech,Finnish,Hindi,Italian,Marathi,Polish,Russian andTelugu.
The Festvox project aims to make the building of new synthetic voices more systematic and better documented,[3] making it possible for anyone to build a new voice. It is distributed under afree software license similar to theMIT License.
Festvox is a suite of tools byAlan W. Black andKevin Lenzo for building synthetic voices for Festival. It includes a step-by-step tutorial with examples in document called "Building Synthetic Voices".[4]
Flite is a small run-time speech synthesis engine developed atCarnegie Mellon University, derived from both Festival and Festvox.[5]
There is a Festivalplug-in forGStreamer. Festival is pre-packaged for severalLinux distributions.
