Festival is a general multi-lingual speech synthesis system
   developed at CSTR. It offers a full text to speech system with
   various APIs, as well an environment for development and research
   of speech synthesis techniques. It is written in C++ with a
   Scheme-based command interpreter for general control.

   Version 1.3.1 (January 1999) is now available for research,
   educational and individual use for free. It has the following
   features
     * English (British and American), Spanish (mexican) and
       Welsh text to speech
     * Externally configurable language independent modules
          + phonesets, lexicons, letter-to-sound rules, tokenizing,
            part of speech tagging, intonation and duration.
     * Waveform synthesizers:
          + diphone based: residual excited LPC (and PSOLA not for
            distribution)
          + MBROLA database support.
     * Portable (Unix) distribution.
     * On-line documentation.
     * SABLE markup, Emacs, client/server (including Java), scripting
       interfaces.

You will also need to install at least one festvox-* (festival voice)
package (infact, the festvox packages are dependent on this package).

-Julian Assange <proff@iq.org>