Installing the Festival Speech Synthesis System with Mavericks. Ask Question Asked 5 years, 3. (one of the creators of Festival): Use the speechtools and Festival packages. But if you must know, I need to access to a portable speech synthesis API. 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. 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 Speech Synthesis System Download For Windows
• Festival Speech Synthesis System Download For Free
• Festival Speech Synthesis System Download For Windows 7

Flite is an open source small fast run-time text to speech engine. Itis the latest addition to the suite of free software synthesis toolsincluding University of Edinburgh's Festival Speech Synthesis Systemand Carnegie Mellon University's FestVox project, tools, scripts anddocumentation for building synthetic voices. However, flite itselfdoes not require either of these systems to compile and run.

The core Flite library was developed by Alan W Black awb@cs.cmu.edu(mostly in his so-called spare time) while employed in the LanguageTechnologies Institute at Carnegie Mellon University. The name'flite', originally chosen to mean 'festival-lite' is perhaps doublyappropriate as a substantial part of design and coding was done over30,000ft while awb was travelling, and (usually) isn't in meetings.

The voices, lexicon and language components of flite, both theircompression techniques and their actual contents were developed byKevin A. Lenzo lenzo@cs.cmu.edu and Alan W Black awb@cs.cmu.edu.

Flite is the answer to the complaint that Festival is too big, too slow,and not portable enough.

o Flite is designed for very small devices, such as PDAs, and alsofor large server machines which need to serve lots of ports.

o Flite is not a replacement for Festival but an alternative run timeengine for voices developed in the FestVox framework where size andspeed is crucial.

o Flite is all in ANSI C, it contains no C++ or Scheme, thus requiresmore care in programming, and is harder to customize at run time.

o It is thread safe

o Voices, lexicons and language descriptions can be compiled(mostly automatically for voices and lexicons) into C representationsfrom their FestVox formats

o All voices, lexicons and language model data are const and in thetext segment (i.e. they may be put in ROM). As they are linked inat compile time, there is virtually no startup delay.

o Although the synthesized output is not exactly the same as the samevoice in Festival they are effectively equivalent. That is, flitedoesn't sound better or worse than the equivalent voice in festival,just faster, smaller and scalable.

o For standard diphone voices, maximum run time memoryrequirements are approximately less than twice the memory requirementfor the waveform generated. For 32bit archtecturesthis effectively means under 1M.

o The flite program supports, synthesis of individual strings or files(utterance by utterance) to direct audio devices or to waveform files.

o The flite library offers simple functions suitable for use in specificapplications.

Flite is distributed with a single 8K diphone voice (derived from thecmu_us_kal voice), a pruned lexicon (derived fromcmulex) and a set of models for US English. Here are comparisonswith Festival using basically the same 8KHz diphone voice

On a 500Mhz PIII, a timing test of the first two chapters of'Alice in Wonderland' (doc/alice) was done. This produces about1300 seconds of speech. With flite it takes 19.128 seconds (about70.6 times faster than real time) with Festival it takes 97 seconds(13.4 times faster than real time). On the ipaq (with the 16KHz diphones)flite synthesizes 9.79 time faster than real time.

Requirements:

Supported platforms:

We have successfully compiled and run on

Previously we supported PalmOS and Windows CE but these seem to be rarenowadays so they are no longer actively supported.

Other similar platforms should just work, we have also cross compiledon a Linux machine for StrongARM. However note that new byte orderarchitectures may not work directly as there is some carefulbyte order constraints in some structures. These are portable but mayrequire reordering of some fields, contact us if you are moving toa new archiecture.

News

New in 2.2 (Oct 2018)o Better qrapheme support (Wilderness Languages) hundreds of new languages

New in 2.1 (Oct 2017)

New in 2.0.0 (Dec 2014)o Indic language support (Hindi, Tamil and Telugu)

New in 1.4.1 (March 2010)o better ssml support (actually does something)

New in 1.4 (December 2009)o crude multi-voice selection support (may change)

New in 1.3-release (October 2005)o fixes to lpc residual extraction to give better quality output

New in 1.2-release (February 2003)o A build process for diphone and clunits/ldom voicesFestVox voices can be converted (sometimes) automatically

Compilation

In general

Where tar is gnu tar (gtar), and make is gnu make (gmake).

Or

Configuration should be automatic, but maybe doesn't work in all casesespecially if you have some new compiler. You can explicitly set thecompiler in config/config and add any options you see fit. Configuretries to guess these but it might be unable to guess for crosscompilation cases Interesting options there are

There are different sets of voices and languages you can select betweenthem (and your own sets if you make config/XXX.lv). For example

Will use the languages and voices defined in config/transtac.lv

Usage:

The ./bin/flite binary contains all supported voices and you maychoose between the voices with the -voice flag and list the supportedvoices with the -lw flag. Note the kal (diphone) voice is a differenttechnology from the others and is much less computationally expensivebut more robotic. For each voice additional binaries that containonly that voice are created in ./bin/flite_FULLVOICENAME,e.g. ./bin/flite_cmu_us_awb. You can also refer to external clustergen.flitevox voice via a pathname argument with -voice (note the pathnamemust contain at least one '/')

If it compiles properly a binary will be put in bin/, note bydefault -g is on so it will be bigger than is actually required

Will produce an 8KHz riff headered waveform file (riff is Microsoft'swave format often called .WAV).

Festival Speech Synthesis System Download For Windows

Will play the text file doc/alice. If the first argument containsa space it is treated as text otherwise it is treated as a filename.If a second argument is given a waveform file is written to it,if no argument is given or 'play' is given it will attempt towrite directly to the audio device (if supported). if 'none'is given the audio is simply thrown away (used for benchmarking).Explicit options are also available.

Will synthesize the file without playing the audio and give a summaryof the speed.

will synthesize the whole of alice into a single file (previoousversions would only give the last utterance in the file, butthat is fixed now).

An additional set of feature setting options are available, these aredebug options, Voices are represented as sets of feature values (seelang/cmu_us_kal/cmu_us_kal.c) and you can override values on thecommand line. This can stop flite from working if malicious valuesare set and therefor this facility is not intended to be madeavailable for standard users. But these are useful fordebugging. Some typical examples are

Use simple concatenation of diphones without prosodic modification

Print sentences as they are said

Make it speak slower

Make it speak higher pitch

The talking clock is an example talking clode as discussed onhttp://festvox.org/ldom it requires a single argument HH:MMunder Unix you can call it

List the voices linked in directly in this build

Speak with the US male rms voice (builtin version)

Speak with the 'Scottish' male awb voice (builtin version)

Speak with the US female slt voice

Speak with AEW voice, download on the fly from festvox.org

Speak with AHW voice loaded from the local file.

You can download the available voices into voices/

Festival Speech Synthesis System Download For Free

and/or

Voice quality

So you've eagerly downloaded flite, compiled it and run it, now youare disappointed that it doesn't sound wonderful, sure its fast andsmall but what you really hoped for was the dulcit tones of a deepbaritone voice that would make you desperately hang on every phrase itmellifluously produces. But instead you get an 8Khz diphone voice thatsounds like it came from the last millenium.

Well, first, you are right, it is an 8KHz diphone voice from the lastmillenium, and that was actually deliberate. As we developed flite wewanted a voice that was stable and that we could directly compare withthat very same voice in Festival. Flite is an engine. We want tobe able take voices built with the FestVox process and compile themfor flite, the result should be exactly the same quality (though ofcourse trading the size for quality in flite is also an option). Theincluded voice is just a sample voice that was used in the testingprocess.

We expect that often voices will be loaded from external files, and wehave now set up a voice repository in

If you visit there with a browser you can hear the examples. You canalso download the .flitevox files to you machine so you don't need anetwork connect everytime you need to load a voice.

We are now actively adding to this list of available voices in English (16)and other languages.

Bard Storyteller: https://github.com/festvox/bard

Festival Speech Synthesis System Download For Windows 7

Bard is a companion app that reads ebooks, both displaying them andactually reading them to you out loud using flite. Bard supports awide range of fonts, and flite voices, and books in text, html andepub format. Bard is used as a evaluation of flite's capabilities andan example of a serious application using flite.