An experimental JAX port of Dia, the 1.6B parameter text-to-speech model from Nari Labs
pip install -U diajax
dia --text "[S1] Dear Jacks, to generate audio from text from any machine. [S2] Any machine? (gasps) How? [S1] With flakes and an axe. (chuckle) " --max-tokens=600import diajax
model = diajax.load()
output = diajax.generate(model, "[S1] Dear Jacks, to generate audio from text from any machine. [S2] Any machine? (laughs) How? [S1] With flacks and an axe. (coughs)")
diajax.save(output)This project is a port of the original Dia model by Nari Labs. We thank them for releasing their model and code, which made this port possible.
This project is licensed under the same terms as the original Dia model. See LICENSE for details.