phonon: WebGPU browser TTS hits 26x real-time on iPhone with a 44MB model, open sourced
blixt · x · 2026-11-04
Developer blixt open-sourced phonon, a WebGPU runtime for Gradium's 31M Phonon TTS model that dramatically outperforms Gradium's own browser package.
- 115x real-time on M3 Max (vs 31x), 73x on RTX 2080 Ti (vs 21x), 26x on iPhone 17 Pro (vs 13x)
- First audio in 3ms on M3 Max, 11ms on iPhone; cached cold start first audio in 46ms
- Weights quantized to 8-bit integers: 44.3MB download vs 66.8MB official
- Every word/token gets start and end timestamps for captions and read-alongs
- Apache-2.0, works in Chrome on macOS/Windows and Safari on iOS
Related event: Open-Source Browser TTS Runtime phonon Runs on WebGPU(2 posts)→
More from Infra
- Prized adds GPU rentals to dev boxes; agent rents a GPU overnight — thisguyknowsai · 2026-11-04
- Superlinked launches SIE Serverless, managed inference for 20+ small models — CShorten30 · 2026-11-04
- Hedra speeds up Krea 3 diffusion transformer 6.9x on AMD Instinct MI355X — henloitsjoyce · 2026-11-04
- Extropic to launch TSUs on SpaceX rocket next year, betting on space datacenters — beffjezos · 2026-11-04
- Volcano Engine's console AI agent analyzes your cloud bill to explain negative balance — vista8 · 2026-11-04
- 8 free GitHub repos with 792K stars that take your AI off Big Tech's servers — alex_verem · 2026-11-04