motionlabs/kokoro-webgpu

Kokoro Text-to-Speech (WebGPU)

A simple React + Vite application for running Kokoro, a frontier text-to-speech model for its size using Transformers.js.

Getting Started

Follow the steps below to set up and run the application.

1. Clone the Repository

Clone the examples repository from GitHub:

git clone https://github.com/hexgrad/kokoro.git

2. Navigate to the Project Directory

Change your working directory to the demo folder:

cd kokoro/kokoro.js/demo

3. Install Dependencies

Install the necessary dependencies using npm:

npm i

4. Run the Development Server

Start the development server:

npm run dev

The application should now be running locally. Open your browser and go to http://localhost:5173 to see it in action.