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.
Online demoThere are two online demonstrations of Festival, where you can synthesise your own sentences:
Current versionVersion 2.4 is available for download. This is the most recent version available for free and unrestricted use.
New in this release:
- Updated HTS and CG engines
- Support for newer compilers
- Bug fixes galore.
- Backwards compatibility with Festival 1.4.3
- English (British and American), Spanish and Welsh text to speech
- Externally configurable language independent modules:
- letter-to-sound rules
- part of speech tagging
- intonation and duration
- Waveform synthesizers:
- Multisyn unit selection engine
- HTS parametric synthesis engine
- Clustergen parametric synthesis engine
- Clunits unit selection engine
- diphone based: residual excited LPC (and PSOLA not for distribution)
- MBROLA database support.
- distributed under a free X11-type licence
- Portable (Unix) distribution
- On-line documentation
- SABLE markup, Emacs, client/server, scripting interfaces.
- Alan W Black (CMU)
- Rob Clark (CSTR)
- Korin Richmond (CSTR)
- Junichi Yamagishi (CSTR)
- Keiichiro Oura (Nitech)
- Simon King (CSTR)
- Paul Taylor
- Richard Caley
- Heiga Zen
ManualThe 2.4 manual is available here.
Mailing listsFestival related mailing lists can be found here.
- The Tools to build Multisyn voices as described in Clark, Richmond & King 2004 are available here.
- SpeechRecorder is a tool for recording audio data on a Mac.
Festival is constantly being improved and added to in continuing our research in speech synthesis at CSTR.
Contact or for more details.