text to speech - chunhualiao/public-docs GitHub Wiki

https://x.com/deedydas/status/1914714739432939999

Deedy @deedydas

4h We just solved text-to-speech AI.

This model can simulate perfect emotion, screaming and show genuine alarm. β€” clearly beats 11 labs and Sesame β€” it’s only 1.6B params β€” streams realtime on 1 GPU β€” made by a 1.5 person team in Korea!!

It's called Dia by Nari Labs.