kale-tts-1-nano: open-source 14.8MB TTS, 125x real-time on WebGPU

NERDDISCO · x · 2026-11-20

NERDDISCO announced kale-tts-1-nano, a 7.5M-parameter TTS model that is only 14.8MB with 10 voices, starting speech in 90ms on a plain CPU and up to 125x faster than real time (25ms startup) on WebGPU. Weights, training scripts, dataset and the full recipe are all open-sourced.

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

Original post →

More from Research

Research channel →