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.
More from Multimodal
- LichtFeld Studio v0.5.4.3 adds community-built SteadySplats and voxelization features — janusch_patas · 2026-10-26
- Hi3D V1.0 open-sourced with 2M training assets and 90% slicing success rate — kimmonismus · 2026-10-26
- Claude Can Replace Your YouTube Thumbnail Designer in 10 Minutes — thedankoe · 2026-10-26
- Multimodal AI Is Not Useless: A Practitioner Pushes Back on Growing Skepticism — thoma_gu · 2026-10-26
- One prompt, full Blender animation: dev says he never touched Blender once — iamfakhrealam · 2026-10-26
- Dense instance segmentation via Muse Wonder + SAM 3.1 on Meta's Model API — nikhilaravi · 2026-10-26