Use syllable breakdown field to automatise TTS
Opened this issue · 0 comments
hardcorekancil commented
The "syllable breakdown" field could be used to feed TTS audio. The idea would be to encode the syllables in machine readable information (e.g. Adébòmí for [a_m.de_h.bo_f.mi_r] or any similar convention) where the machine could assign a pre-recorded audio file to each segment.