Small Parameter Voice Model Leads in Multilingual Capabilities

mattturck · x · 2026-07-16

A reshared post introduces GradiumAI's Phonon: despite having only 100 million parameters, it already leads in English. Now, its word error rates in French, German, and Spanish are also lower than NVIDIA's Magpie (357 million parameters) and Neuphonic's NeuTTS Nano (229 million parameters).

The post also emphasizes its support for high-quality voice cloning and its smaller model size. The original post includes comprehensive multilingual benchmarks and access links.

Original post →

More from Multimodal

Multimodal channel →