Four TTS models small enough to run on CPU, smallest just 1.4M params
vanstriendaniel · x · 2026-11-07
Daniel van Strien rounds up recent text-to-speech models tiny enough to run on a CPU: phonon-31m-en (31M), Paradee-8M (7.9M), Leokani-tts (7M, with a 4.5M variant) and PiVo (1.4M, vocoder included). Paradee runs 62x real time on a single CPU thread; all are on Hugging Face.
Related event: Developer Rounds Up Four Tiny CPU-Runnable TTS Models(2 posts)→
More from Infra
- Decision models fix a pricing inefficiency: prefill workloads subsidize decode, argues sh_reya — hugobowne · 2026-11-07
- Team weighs multi-GPU cluster vs one fat workstation to escape cloud API rate limits — Decent_Wing_4393 · 2026-11-07
- AMD's Halo Station packs 96 cores, 2TB RAM, 576GB GPU memory — for $100k-$150k — Sea_Emergency_8458 · 2026-11-07
- Satnam Singh: AI Is Dissolving the Hardware/Software Boundary for Good — satnam6502 · 2026-11-07
- Data centers' water use is just ~4% of US golf course irrigation, study argues — kimmonismus · 2026-11-07
- Data centers' water use vastly overstated: just 4% of US golf course irrigation — kimmonismus · 2026-11-07