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)→
More from Research
- WorldTrace beats sliding window recall by 32.6% at same cache size, tops all 12 LoopBench conditions — cindy_x_wu · 2026-11-21
- Proposed proof of Generalized Riemann Hypothesis released; mathematician stresses it is entirely human, no AI — paulabartabajo_ · 2026-11-21
- Arcfront turns real hospital and factory work records into RL environments and frontier model evals — rohanpaul_ai · 2026-11-21
- Goodfire probes Inkling 2 Mini: looped model layers read from "future" layers — fatihdin4en · 2026-11-21
- Terence Tao offers a bet to anyone who really believes RH will be proved next year — jaivin · 2026-11-21
- Terence Tao: AI is winning at math but we've learned almost nothing from it — bansalg_ · 2026-11-21