from the authors:
The Festival Speech Synthesis System is a general multi-lingual
text-to-speech system for Unix platforms. It is written in C++ and
includes a Scheme-based scripting language. Included with Festival
are lexicons and voices that together form a whole text-to-speech
system.
For output via esd do:
(Parameter.set 'Audio_Method 'esdaudio)
NAS and direct output are documented in section 23 of the users'
manual.
If you need the OGI extensions, install ports/audio/festival+OGI instead.
Trevor Johnson
This is the Oxford Advanced Learner's pronunciation dictionary
(British English), modified for the Festival speech synthesis
system.
US English Scottish male voice by the Language Technologies Institute
at Carnegie Mellon University constructed from phonetically balanced,
US English single speaker database designed for unit selection
speech synthesis research.
The speaker is very experienced in building synthetic voices and
matched prompted US English, though his vowels are very different
from US English vowels. Scottish English speakers will probably
find synthesizers based on this voice strange.
(voice_cmu_us_awb_arctic_clunits)
US English male voice by the Language Technologies Institute at
Carnegie Mellon University constructed from phonetically balanced,
US English single speaker database designed for unit selection
speech synthesis research.
(voice_cmu_us_bdl_arctic_clunits)
US English female voice by the Language Technologies Institute at
Carnegie Mellon University constructed from phonetically balanced,
US English single speaker database designed for unit selection
speech synthesis research.
(voice_cmu_us_clb_arctic_clunits)
US English Canadian male voice by the Language Technologies Institute
at Carnegie Mellon University constructed from phonetically balanced,
US English single speaker database designed for unit selection
speech synthesis research.
(voice_cmu_us_jmk_arctic_clunits)
US English Indian male voice by the Language Technologies Institute
at Carnegie Mellon University constructed from phonetically balanced,
US English single speaker database designed for unit selection
speech synthesis research.
(voice_cmu_us_ksp_arctic_clunits)
US English male voice by the Language Technologies Institute at
Carnegie Mellon University constructed from phonetically balanced,
US English single speaker database designed for unit selection
speech synthesis research.
(voice_cmu_us_rms_arctic_clunits)
US English female voice by the Language Technologies Institute at
Carnegie Mellon University constructed from phonetically balanced,
US English single speaker database designed for unit selection
speech synthesis research.
(voice_cmu_us_slt_arctic_clunits)
Quality free Czech diphone database.
Primary goal is for speech system Festival but it's not limited on it. Sources,
sound files and boundaries are available so it can be used in other free
speech synthesizer systems too.