Gradium open-sources Phonon, a 31M-parameter on-device TTS model
Gradium
Released October 20, 2026, Phonon comes in 31M and 40M parameter variants; the English 31M model is Apache 2.0 at 64 MB quantized, while the 40M and multilingual weights are CC BY-NC. It runs without PyTorch through a Rust runtime on CPU, GPU, NPU and WASM, starts speaking in about 7 ms on a laptop CPU, and ships 37 built-in voices.
Why it matters
Sub-50M open TTS makes local, offline voice a plausible default for apps that cannot call an API.
Importance: 2/5
notable update (minor version with real changes)
Sources
official
gradium/phonon-31m-en - Hugging Face