- Home
- Text-to-Speech Software
- Festival Speech Synthesis System
On the recordRead 12 Oct 202618 facts
Festival Speech Synthesis System
Festival Speech Synthesis System · Edinburgh, Scotland, United Kingdom · founded 1984
Plans and prices
Festival 2.4
Free
Free software; voice and lexicon licenses may have restrictions
Read 12 Oct 2026 · cstr.ed.ac.uk
On the record
- API access
- Yescstr.ed.ac.uk · read 20 Sep 2026
- Build requirements
- Running Festival requires a C++ compiler and GNU Make.cstr.ed.ac.uk · read 12 Oct 2026
- Commercial use
- Yescstr.ed.ac.uk · read 20 Sep 2026
- Configuration
- Language modules can be configured for phonesets, lexicons, letter-to-sound rules, tokenizing, part-of-speech tagging, intonation, and duration.cstr.ed.ac.uk · read 12 Oct 2026
- Interfaces
- It provides interfaces through shell commands, a Scheme interpreter, C++ library, Java, and Emacs.cstr.ed.ac.uk · read 12 Oct 2026
- Languages
- The site lists British and American English, Spanish, and Welsh text-to-speech, and says English is the most advanced.cstr.ed.ac.uk · read 12 Oct 2026
- License
- Festival and the speech tools use an X11-type license that allows commercial and non-commercial use.cstr.ed.ac.uk · read 12 Oct 2026
- Maintainer context
- The Centre for Speech Technology Research is an interdisciplinary University of Edinburgh research centre founded in 1984.cstr.ed.ac.uk · read 12 Oct 2026
- Markup and integration
- The system lists SABLE markup, Emacs, client/server, and scripting interfaces.cstr.ed.ac.uk · read 12 Oct 2026
- Purpose
- Festival is a framework for building speech synthesis systems and provides full text-to-speech functionality.cstr.ed.ac.uk · read 12 Oct 2026
- Source distribution
- The distribution includes full C++ source, a SIOD interpreter, Scheme library, Edinburgh Speech Tools, and documentation.cstr.ed.ac.uk · read 12 Oct 2026
- Support
- The project page links to Festival related mailing lists hosted by FestVox.cstr.ed.ac.uk · read 12 Oct 2026
- Voice building
- The project points to Carnegie Mellon’s FestVox project for tools and documentation to build new voices.cstr.ed.ac.uk · read 12 Oct 2026
- Voice engines
- Included waveform synthesis options include Multisyn, HTS, Clustergen, Clunits, diphone-based synthesis, and MBROLA database support.cstr.ed.ac.uk · read 12 Oct 2026
- Voice restrictions
- The download page notes that some voices have license restrictions and that the OALD UK lexicon is restricted to non-commercial use.cstr.ed.ac.uk · read 12 Oct 2026
