A vocal tract you play like a synth. A buzzing source, like vocal folds, drives a model of the throat and mouth that you reshape with tongue, lips and soft palate controls to sing vowels and slur consonants.
The idea
Speech is made by a tube, not by samples. Air sets the vocal folds buzzing, and the shape of the tract above them filters that buzz into the vowels and consonants we recognise. Mouth Synth models exactly that, in the lineage of Neil Thapen's Pink Trombone: a chain of short tube sections, each with its own width. Sound reflects wherever the width changes, and the resonances that survive are the formants you hear as a vowel.
Moving the tongue slides the tightest point of the tube forward and back and raises or lowers it, which is the whole difference between "aah", "eee" and "ooh". A separate constriction pinches the tube at one spot, near the teeth for an "s" or at the lips for an "f", and when it closes fully and opens again you hear the small pop of a "p" or a "t". Opening the soft palate lets sound through the nose for hums and the "m", "n" and "ng" family.
