Gradium Open-Sources Phonon: 31M On-Device TTS at 64MB, 7ms Latency
lmoroney · x · 2026-10-21
Gradium has open-sourced Phonon, a family of tiny text-to-speech models built to run entirely on local hardware. The English 31M model is about 64 MB under Apache 2.0, ships with 37 voices, and reportedly reaches first audio in 7 ms on a MacBook Air. The author breaks down the release, how it works, and which models are commercially usable.
Related event: Gradium Open-Sources Phonon, On-Device TTS Models Under 50M Parameters(16 posts)→
More from Multimodal
- AI-generated Star Wars-style game demo shows a flyable desert world with TIE fighters — jasonkneen · 2026-10-29
- LiquidAI's LFM3-Audio-2B audio model trends on Hugging Face — LiquidAI · 2026-10-29
- Generating pop-art Halloween portraits with Flora and a vibe board — round · 2026-10-29
- Generating K-Pop music videos with a Claude Music Video skill, no MCP needed — AIandDesign · 2026-10-29
- Granary-v2 open speech model expands to 48 languages with open data and pipeline — rdesh26 · 2026-10-29
- ciguleva shares surreal AI artwork "Under the Hood of the Universe" — ciguleva · 2026-10-29