Soprano: Ultra-Lightweight On-Device TTS Achieving 20x Real-Time on CPU

tom_doerr · x · 2026-07-21

Soprano is a newly released ultra-lightweight on-device text-to-speech (TTS) model. It boasts highly efficient generation capabilities, achieving 20x real-time generation on CPU and an impressive 2000x on GPU. Furthermore, it operates on under 1GB of memory, making it highly suitable for local deployment.

Original post →

More from Models

Models channel →