CPU-runnable open TTS models are piling up, starting with open-weights kale-tts-1

Kyrannio · x · 2026-11-21

NERDDISCO released kale-tts-1, their first Hugging Face TTS release with open weights in base/tiny/nano sizes, plus dataset and demo. Commenters note a broader trend: many CPU-based TTS models have dropped recently, a space previously unoptimized for size or quality, with early feedback favoring the Kenzie US voice.

Related event: 14.8MB Open-Source TTS Model kale-tts-1 Runs on CPU with 90ms Latency(7 posts)→

Original post →

More from Multimodal

Multimodal channel →