Introducing TTS WebGPU: The first ever text-to-speech web app built with WebGPU acceleration! 🔥 High-quality and natural speech generation that runs 100% locally in your browser, powered by OuteTTS and Transformers.js.🤗 Try it out yourself! Demo + source code below 👇

The model is multilingual (English, Chinese, Korean & Japanese) and even supports zero-shot voice cloning! 🤯 Stay tuned for an update that will add these features to the UI! More samples:

Huge shout-out to @OuteAI for their amazing model (OuteTTS-0.2-500M) and for helping us bring it to the web! 🤗 Together, we released the outetts NPM package, which you can install with `npm i outetts`. 🧑‍💻 Source code: 🔗 Demo:

🔥

Wish WebGPU worked with @brave in Ubuntu.

What’s the best speech-to-text model on WebAI these days? Chrome’s web speech API a bit outdated now

For its size, I'd probably say Piper (see for samples). The community has even got it running in WASM too!

TypeError: navigator.gpu is undefined

Thanks @xenovacom for sharing the demo. I added PR to support LLM in a browser extension. Can you reivew my PR? I'm happy to add more modalities into chrome extension