festvox-kallpc8k binary package in Ubuntu Xenial amd64

 This is a diphone database for festival that uses 8k samples so it takes up
 a minimum of disk space. Using this diphone database, festival also converts
 text to speech faster than with the 16k version. However, the sound quality
 is not as good.
 .
 The voice contained in this database is an American English male speaker.
 A different American English voice can be found in the festvox-kdlpc16k
 package if you dislike this one.

Source package