|   CMU Speech Software   |   CMU Speech Group   |  

FestVox Download

    Festival Manual
    EST Manual

Voice Demos
Limited Domain
Example Databases
Mailing Lists
Search Documents
Contributed parts

University of Edinburgh Festival Speech Synthesis System
University of Edinburgh's Festival Speech Synthesis Systems is a free software multi-lingual speech synthesis workbench that runs on multiple-platforms offering black box text to speech, as well as an open architecture for research in speech synthesis. It designed as a component of large speech technology systems.

This site is the main US mirror.

The distribution here includes source for the Edinburgh Speech Tools Library and Festival itself. 15 Voices are also provided for US English, other voices are available elsehwere on this site and instructions to build new voices are given here.

Festival 2.5-release is now released (25th December 2017)

Although we agressively attempt to run Festival on all platforms we can get access to it is not always the case that it works out of the box. The hardest requirement is probably having a working and compatible audio system, simple as audio is supposed to be in our experience we find a wide range of standards. We do give pointers for dealing with audio systems we don't yet support, and offer and external playing mechainsm so if you have any programs that can play sound Festival can usually use that.

Festival is primarily designed as a component of a larger speech applicationm hence we provide a number of APIs. It can be used to simply synthesize text files but to people who think command line interfaces are quaint you might find this not what you are looking for.

The system was (and still is) primarily developed under Unix (Linux, FreeBSD and Solaris) because the authors are by far most familar with these. However the system has been ported to Windows and is used in a number of real applications on that platform. Although there is full support for Windows we do not yet feel it is as mature or stable the versions under Unix.

The system is written in C++ which means with every new version of of each vendor's C++ compiler that is released our system probably wont compile without minor changes. We try to keep up with new versions as quickly as we can, and make patches or instructions available for new versions as soon as we can.

CMU/LTI This page is maintained by Alan W Black (awb@cs.cmu.edu)
Festvox is a project within LTI at Carnegie Mellon University