Zyphra's ZONOS3-Mini is an Apache-2.0 TTS model that clones voices in a browser
ZONOS3-Mini is an 800M-parameter MoE text-to-speech model with about 100M active, Apache-2.0 weights, voice cloning and runtimes for browsers, Macs and SGLang.
Topic · 5 stories
5 stories tagged webgpu on AI Tamer, newest first.
ZONOS3-Mini is an 800M-parameter MoE text-to-speech model with about 100M active, Apache-2.0 weights, voice cloning and runtimes for browsers, Macs and SGLang.
Underdog's Woof TTS: ~31.7 MB / ~30.7M params, WebGPU in-browser demo at underdog.ai/escape. License CC BY-NC 4.0. No confirmed Hub GA.
A new tract example runs SD 1.5 on the visitor's GPU via WebGPU and wasm. The 2.1 GB of weights come from Hugging Face and nothing leaves the machine.
Mirai's 16 October post points at uzu.run, a browser preview of local models over WebGPU. The engine's WebGPU backend is still an unmerged draft.
Cheng Lou published Handwired, a toy that turns ordinary JavaScript into an exact neural net with no training. The repository is MIT.