Tiny-voca debuts 18 MB English TTS model trained on synthetic speech for $9
Tiny-voca released an 18 MB English text-to-speech model with 4.5M parameters, trained solely on synthetic speech, running 70x faster than real time on CPU at a $9 price and under $10 in training costs.
Read the full story at AlphaSignal ↗
Timeline · 1 report
- 2026-11-17 12:17 · AlphaSignal
Tiny-voca Packs Two AI Voices Into an 18 MB Model for $9