Festival Speech Synthesis System

cstr.ed.ac.uk

Free plan WindowsmacOSLinuxAPISelf-hosted

Visit cstr.ed.ac.uk

Spec score 8.5 #53 of 223 in Text-to-Speech Software

Spec sheet

Purpose: Festival is a framework for building speech synthesis systems and provides full text-to-speech functionality.Read 12 Oct 2026 · cstr.ed.ac.uk
Platforms: The download page requires a Unix-like environment and gives Linux, FreeBSD, OSX, and Cygwin under Windows as examples.Read 12 Oct 2026 · cstr.ed.ac.uk
Free plan: YesRead 20 Sep 2026 · cstr.ed.ac.uk
Support: The project page links to Festival related mailing lists hosted by FestVox.Read 12 Oct 2026 · cstr.ed.ac.uk
License: Festival and the speech tools use an X11-type license that allows commercial and non-commercial use.Read 12 Oct 2026 · cstr.ed.ac.uk
Headquarters: Edinburgh, Scotland, United KingdomRead 28 Sep 2026 · cstr.ed.ac.uk
API access: YesRead 20 Sep 2026 · cstr.ed.ac.uk
Build requirements: Running Festival requires a C++ compiler and GNU Make.Read 12 Oct 2026 · cstr.ed.ac.uk
Commercial use: YesRead 20 Sep 2026 · cstr.ed.ac.uk
Configuration: Language modules can be configured for phonesets, lexicons, letter-to-sound rules, tokenizing, part-of-speech tagging, intonation, and duration.Read 12 Oct 2026 · cstr.ed.ac.uk
Interfaces: It provides interfaces through shell commands, a Scheme interpreter, C++ library, Java, and Emacs.Read 12 Oct 2026 · cstr.ed.ac.uk
Languages: The site lists British and American English, Spanish, and Welsh text-to-speech, and says English is the most advanced.Read 12 Oct 2026 · cstr.ed.ac.uk
Maintainer context: The Centre for Speech Technology Research is an interdisciplinary University of Edinburgh research centre founded in 1984.Read 12 Oct 2026 · cstr.ed.ac.uk
Markup and integration: The system lists SABLE markup, Emacs, client/server, and scripting interfaces.Read 12 Oct 2026 · cstr.ed.ac.uk
Source distribution: The distribution includes full C++ source, a SIOD interpreter, Scheme library, Edinburgh Speech Tools, and documentation.Read 12 Oct 2026 · cstr.ed.ac.uk
Voice building: The project points to Carnegie Mellon’s FestVox project for tools and documentation to build new voices.Read 12 Oct 2026 · cstr.ed.ac.uk
Voice engines: Included waveform synthesis options include Multisyn, HTS, Clustergen, Clunits, diphone-based synthesis, and MBROLA database support.Read 12 Oct 2026 · cstr.ed.ac.uk
Voice restrictions: The download page notes that some voices have license restrictions and that the OALD UK lexicon is restricted to non-commercial use.Read 12 Oct 2026 · cstr.ed.ac.uk