kale-tts-1-nano: a 7.5M-param, 14.8MB TTS that speaks in 90ms on CPU

NERDDISCO · x · 2026-11-20

NERDDISCO released kale-tts-1-nano: a 7.5M-parameter, 14.8MB text-to-speech model with 10 voices that starts speaking in 90ms on a plain CPU, and up to 125x faster than real time with 25ms startup on WebGPU. Weights, training scripts, dataset and the full recipe are all open, targeting fully local speech on CPU-only devices.

Related event: NERDDISCO releases kale-tts-1, a 14.8MB open TTS family(7 posts)→

Original post →

More from Research

Research channel →