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)→
More from Multimodal
- Full workflow fixes Fable 5.2 video audio entirely inside Claude — AIwithGhotai · 2026-11-21
- NVIDIA ships Alpamayo 2 Edge, a 2B-parameter in-vehicle reasoning VLA model — NVIDIAAI · 2026-11-21
- Creator shows HeyGen-powered video edit: 'editing to another level' — aziz4ai · 2026-11-21
- AI-built oil painting engine: 2,300 commits in 8 days as Claude Code runs a 'studio' of sessions — FotoRe_store · 2026-11-21
- "AGI Before GTA6": AI-Generated Music Video Riffs on 13-Year GTA VI Wait — Yamapama · 2026-11-21
- Meta's AVTR adds visual imagination to multimodal reasoning, +4.5 pts across 16 benchmarks — liuzhuang1234 · 2026-11-21