ModelKitten-TTS V0.8
Kitten-TTS V0.8
An early experimental version of the speech synthesis model released by KittenML. It was later fully superseded by Kitten-TTS 2.
Timeline (last 90 days)
Oct 22
Kitten-TTS 2 is a completely new architectural rewrite from V0.8 to 2, with changes including improved speech quality, introduction of ternary weights, zero-shot voice cloning, multilingual support, and emotion/stress control.
Unverified50%