from the NetBSD maintainer:

This voice provides an American English male voice using a residual
excited LPC diphone synthesis method.  It uses the CMU Lexicon
pronunciations.  Prosodic phrasing is provided by a statistically
trained model using part of speech and local distribution of breaks.
Intonation is provided by a CART tree predicting ToBI accents and
an F0 contour generated from a model trained from natural speech.
The duration model is also trained from data using a CART tree.

WWW:  http://www.cstr.ed.ac.uk/projects/festival/

Trevor Johnson