The Festival Speech Synthesis System

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, from Java, and an Emacs interface. Festival is multi-lingual (currently English (British and American), and Spanish) though English is the most advanced. Other groups release new languages for the system. And full tools and documentation for build new voices are available through Carnegie Mellon's FestVox project (http://festvox.org)

The system is written in C++ and uses the Edinburgh Speech Tools Library for low level architecture and has a Scheme (SIOD) based command interpreter for control. Documentation is given in the FSF texinfo format which can generate, a printed manual, info files and HTML.

Festival is free software. Festival and the speech tools are distributed under an X11-type licence allowing unrestricted commercial and non-commercial use alike.

Current version

A beta version of 2.0 (labelled 1.95-beta) is available for download. This is the most recent version available for free and unrestricted use. This version is functionally equivalent to 2.0, but we are holding back changing the number to 2.0 until we can accommodate compatibility with newer versions of compilers. New in this release are:

HTS hidden Markov model based synthesis engine from Nagoya Institute of Technology.
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
bug fixes galore.

Other features include:

Backwards compatibility with Festival 1.4.3
English (British and American), Spanish and Welsh text to speech
Externally configurable language independent modules:
- phonesets
- lexicons
- letter-to-sound rules
- tokenizing
- part of speech tagging
- intonation and duration
Waveform synthesizers:
- diphone based: residual excited LPC (and PSOLA not for distribution)
- MBROLA database support.
- distributed under a free X11-type licence
- generalisation of stats modules, ngram, CART, wfst with viterbi so they can be shared more easily
- Initial JSAPI support
- XML load for Relations
Portable (Unix) distribution
On-line documentation
SABLE markup, Emacs, client/server (including Java), scripting interfaces.

Current Personnel

Past Personnel

Paul Taylor
Richard Caley

Manual

The 1.4.x manual is available here.

Mailing lists

Festival related mailing lists can be found here.

FAQs

A short Festival FAQ is available here.

Future

Festival is constantly being improved and added to in continuing our research in speech synthesis at CSTR, partly through Cougar and Expressions projects

Funding

Work on festival is funded from a variety of sources. Recent funding includes that from: The Engineering and Physical Sciences Research Council (EPSRC GR/R94688/01); Information Society Technologies (IST-1999-10982, IST-1999-29078, IST-2001-32311)

Contact or for more details.

[ download ]