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, and an Emacs interface. Festival is multi-lingual, we have develeoped voices in many languages including English (UK and US), Spanish and Welsh, though English is the most advanced.

The system is written in C++ and uses the Edinburgh Speech Tools 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.

The latest details and a full software distribution of the Festival Speech Synthesis System are available through its home page which may be found at http://www.cstr.ed.ac.uk/projects/festival.html

Languages - Voices and languages for festival

Tips - Useful tips about festival development, usage and setup

Links - Link to similar projects

2009/11/30

Festival windows binary was uploaded as a part of the upcoming release. Get it here: http://prdownload.berlios.de/festlang/festival-win-1.96b.7z

2009/07/28

The very good Polish voice is finally released. It’s an amazing chunk of data. See the announcement. http://lists.berlios.de/pipermail/festlang-talk/2009-July/003276.html. Get the voice here at http://festvox.org/voices/polish/

2009/03/14

I started my blog some time ago at http://nshmyrev.blogspot.com. I think it will be popular one day.

2009/02/22

New release of msu_ru_nsh_clunits is out.

2008/11/14

We are please to inform you the release of the Speech Signal Processing Toolkit (SPTK) version 3.2, which is availble at http://sp-tk.sourceforge.net/

2008/11/08

The Blizzard 2008 results are released. Find them at http://www.synsig.org/index.php/Blizzard_Challenge_2008#Papers

2008/10/17

festival-freebsoft-utils 0.10 released. What is new in version 0.10?

• Speech Dispatcher support works again with recent versions of libc/iconv.
• TMPDIR environment variable is honored even when the related Festival bug is present.
• Bug fixes.

2008/06/27

We are please to inform you the release of HMM-based Speech Synthesis System (HTS) version 2.1. Please check http://hts.sp.nitech.ac.jp/

2008/06/19

The Free(b)soft project is pleased to announce the release of festival-czech 0.3, a general support for the Czech language in the Festival speech synthesis system. Together with voice-czech-ph, a Festival Czech diphone database, it makes a complete Czech speech synthesis implemented in Festival.

2008/06/13

HTS-2.1RC2 is out. This is the final release candidate.

2008/03/24

HTS-2.1RC1 is out. The main feature is CSMAPLR adaptation.

2007/12/21

http://sourceforge.net/projects/dvagar project has started support for gnuspeech trm in festival!

2007/11/23

Freebsoft festival utils version 0.8 are released http://www.freebsoft.org/festival-freebsoft-utils

2007/11/01

HTS-2.1 alpha is out. The main feature is Global Variance in speech parameter generation algorithm.

2007/09/19

The results of Blizzard Challenge are available here: http://festvox.org/blizzard/bc2007/index.html

2007/05/05

Blizzard Challenge started listening tests. The Blizzard Challenge 2007 online registration pages are:

For speech experts

For real users

Only speech experts should register through the URL for speech experts above.

Three sections of the speech synthesis evaluation are similar in style to some sections from last year, but the first two sections are new.

2007/03/30

Festival-si project released Sinhala voice http://www.ucsc.cmb.ac.lk/ltrl

2007/02/06

CFP: Special Session on “Speech and language technology for less-resourced languages” is searching for speakers. Deadline is in March, so there is time to prepare submission. See http://lists.berlios.de/pipermail/festlang-talk/2007-February/001539.html for details.

2007/01/24

The call for participation in the third Blizzard Challenge is posted. Blizzard is a multi-site challenge to build a synthetic voice from a common database that will be evaluated by a large number of listeners. http://festvox.org/blizzard/index.html

2007/01/21

Festvox-2.1 is released! Let’s hope, we’ll see new festival release soon.

http://lists.berlios.de/pipermail/festlang-talk/2007-January/001519.html

2007/01/01

Happy New Year

2006/12/29

We are please to inform you the release of HMM-based Speech Synthesis System (HTS) version 2.0 release December 29, 2006 for HMM-based speech synthesis. Please check http://hts.sp.nitech.ac.jp/

2006/12/25

Searchable archives of festival mailing lists are now working on MARC:

http://marc.theaimsgroup.com/?l=festvox-talk http://marc.theaimsgroup.com/?l=festlang-talk

2006/12/06

Updated OGI voice are released http://speech.bme.ogi.edu/tts/download/index.html

2006/11/12

Russian clustergen voice is released. See Festlang project page for downloads.

2006/10/20

speechd-el 2.1 released, a framework for TTS in emacs

2006/09/06

The Blizzard Challenge 2006 consisted on 14 different systems, results of the evaluation and the papers describing the systems are available here