tiny-voca: an 18MB, 4.5M-param TTS model trained without any real human voice, runs on CPU
Dan_Jeffries1 · x · 2026-11-15
Developer @n4ze3m released tiny-voca, a text-to-speech model that has never heard a real human voice during training.
- 4.5M parameters, only 18 MB in size
- Runs entirely on a CPU
The ultra-lightweight experiment points to a minimal, fully synthetic training approach for on-device speech synthesis.
Related event: tiny-voca: 4.5M-Parameter TTS Trained Fully on Synthetic Speech(4 posts)→
More from Multimodal
- Photographer crafts AI-generated digital muse Nous Girl on faux magazine cover — alexcovo_eth · 2026-11-22
- Turn any Google Maps location into a cinematic drone shot with AI — aziz4ai · 2026-11-22
- Open-source world model PAN 2 wows with GTA-like physics in driving demos — LinusEkenstam · 2026-11-22
- pi-H3 open-sourced: 768p video in under 40s on one RTX 3090 — linoy_tsaban · 2026-11-22
- 2D-to-3D character experiment: hand-drawn illustration becomes consistent 3D render — azed_ai · 2026-11-22
- "River Clash": AI-generated rural action short film with prompts included — propmt07 · 2026-11-22