Festival Speech Synthesis System
| Developer(s) | Centre for Speech Technology Research (CSTR) of the University of Edinburgh |
|---|---|
| Preview release | 2.1 / November 2010 |
| Written in | C++ |
| Operating system | Cross-platform |
| Type | Speech synthesizer |
| License | similar to MIT License (Free software) |
| Website | www.cstr.ed.ac.uk/projects/festival |
Festival is a general multi-lingual speech synthesis system originally developed by Alan W. Black at Centre for Speech Technology Research (CSTR) at the University of Edinburgh. Substantial contributions have also been provided by Carnegie Mellon University and other sites. It is distributed under a free software license similar to the BSD License.
It offers a full text to speech system with various APIs, as well as an environment for development and research of speech synthesis techniques. It is written in C++ with a Scheme-like command interpreter for general customization and extension.[1]
Festival is designed to support multiple languages, and comes with support for English (British and American pronunciation), Welsh, and Spanish. Voice packages exist for several other languages, such as Castilian Spanish, Czech, Finnish, Hindi, Italian, Marathi, Polish, Russian and Telugu.
Contents |
[edit] Festvox
The Festvox project aims to make the building of new synthetic voices more systematic and better documented, making it possible for anyone to build a new voice. It is distributed under a free software license similar to the MIT License.
Festvox is a suite of tools for building synthetic voices for Festival. It includes a step-by-step tutorial with examples in document called Building Synthetic Voices.
[edit] Flite
Flite is a small run-time speech synthesis engine developed at Carnegie Mellon University. It is derived from Festival, originally from the University of Edinburgh, and the Festvox project from Carnegie Mellon University.
[edit] Linux compatibility
There is a Festival plug-in for GStreamer. Festival is pre-packaged for several Linux distributions.
 |
A recording of this article made with text2audio script [2], which uses Festival Speech Synthesis System.
|
| Problems listening to this file? See media help. | |
[edit] See also
- Flinger - FestivaL sINGER. MIDI based Festival interface for producing synthesized singing.
- MBROLA, which Festival can optionally use as a back-end.
- HTS, which Festival can also use as a back-end.
- vozMe, which uses Festival to provide online text to speech.
- The Cepstral speech synthesis engine can be used with Festival.
- FreeTTS is a speech synthesis system written in Java, and based upon Flite
- Audacity to record the Festival output in a mp3 or ogg file.
[edit] External links
- The Festival Speech Synthesis System
- Festival at CMU
- Festvox
- Flite - a small, fast run time synthesis engine
- Cerva - a Python+GTK Festival frontend
- Carnival - a GUI for Festival
- KTTS - a KDE frontend for speech synthesis that supports Festival
- Fala - a GNOME Festival frontend
- Speech Synthesis & Analysis Software
- HTS - HMM-based Speech Synthesis System
- eGuideDog - miscellaneous speech software, including a version of Festival for Windows
- ML-FLite - Multilanguage FLite (italian and english voice)
- ML-FreeTTS - Multilanguage FreeTTS (italian and english voice)
- LHC Announcer - CERN Large Hadron Collider event announcer based on Festival
[edit] References
- ^ "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."[1]
- ^ http://www.taggedzi.com/text2audio.html
|
|||||||||||||||||||||||
