ooof, that's cool
but also scary
we can't take a familiar voice on the phone for granted anymore
that's why we built TavKey 馃悽
Jack Dorsey announced a new full-duplex speech model, called Dessa.
Dessa was trained solely on voice conversations, with no text data or pretrained models.
Currently, only demo samples are available, but they far surpass anything else in emotional expression and natural feel.
Voice models will be everywhere 馃憖