Festival

From LinuxReviews
Jump to navigationJump to search
Festival
Developer(s)Centre for Speech Technology Research (CSTR) of the University of Edinburgh
Initial releaseOctober 12, 2004; 17 years ago (2004-10-12)
Stable release
2.5.1 / July 6, 2020; 17 months ago (2020-07-06)
Repositoryhttps://github.com /festvox/festival
Written inC++
Operating systemCross-platform
TypeSpeech synthesizer
LicenseSpecial license similar to the MIT Software License
Websitewww.cstr.ed.ac.uk/projects/festival/
Text-speak.png

Festival is a text to speech engine developed by the British at the Centre for Speech Technology Research (CSTR) division at the University of Edinburgh. It sounds very robot-like. The speech it creates is understandable but it is not anything remotely close human-sounding. It works, and it can be used for text to speech, but it is not the best free software alternative.

Installation[edit]

The basic festival software is typically available as package named festival but the optional voice packages tend to be named festvox-{voice} (festvox-clb-arctic-hts, festvox-kal-diphone, etc).

Voice files are placed in /usr/share/festival/voices/us/

Basic Use[edit]

Festival can say anything piped to it as long as the -tts option:

echo 'hello' | festival --tts

You can pipe files to festival and have them read:

echo "Hello world" > example.txt
festival --tts < example.txt

Festival can be configured by creating a $HOME/.festivalrc configuration file.

Festival will create a incriminating text file called $HOME/.festival_history with every command sent to it.

Festival is one of many programs that can be used with the Linux speech-dispatcher daemon. Programs like Kmouth will use Festival for text-to-speech if speech-dispatcher is configured to use it (Festival not the default on any GNU/Linux distribution we are aware of).

Audio Quality[edit]

The text to speech output generated by Festival does not sound very natural, it is very robot-like. It is understandable. It's just not very human-sounding and it is not very impressive compared to commercial solution and it is not as good as the free software mimic alternative.

echo 'Hello, this is a test of the emergency broadcasting system' | festival --tts

Alternatives[edit]

Free Text To Speech Synthesis Software
Program rating example voice
espeak-ng
v1.50
Sad hyemi2.jpgSad hyemi2.jpg default
festival
2.5.0
Kim.Se-jeong.confused.jpgKim.Se-jeong.confused.jpgKim.Se-jeong.confused.jpg default
flite
1.3 (2005)
Frustrated stallman cropped.jpg default
mimic
v1.3.0.1
Hyuna-approves.jpgHyuna-approves.jpgHyuna-approves.jpgHyuna-approves.jpg ab
slt

See Text to Speech synthesis software for a indepth comparison of free text to speech software.

See also[edit]

  • Mimic, another text to speech synthesis tool.
  • Kmouth, a KDE program where you can type text and have it read out loud.

Links[edit]

The Festival homepage is at www.cstr.ed.ac.uk /projects/festival/. The source code repository is at github.com /festvox/festival.


Add your comment
LinuxReviews welcomes all comments. If you do not want to be anonymous, register or log in. It is free.