A ThreeJS-powered 3D avatar that animates facial expressions based on input text, leveraging Azure APIs for text-to-speech. This project is suitable for developers looking to integrate interactive virtual humans into web applications, offering a visually engaging way to deliver spoken content.

How It Works

The avatar utilizes ThreeJS for rendering the 3D model in a web browser. Speech synthesis is handled by Azure Cognitive Services Text to Speech, which generates audio and potentially accompanying visemes (facial movement data). These visemes are then mapped to the avatar's facial rig to create synchronized lip-sync and expressions, providing a lifelike conversational experience.

Quick Start & Requirements

• Install: yarn install
• Run: yarn start
• Backend: Requires bornfree/talking_avatar_backend repository for text-to-speech conversion.
• Prerequisites: Node.js, Yarn, Azure API keys.

Highlighted Details

• ThreeJS-powered 3D rendering.
• Azure Cognitive Services integration for speech.
• Potential for ChatGPT integration for conversational AI.

Maintenance & Community

No specific community channels or maintenance details are provided in the README.

Licensing & Compatibility

The license is not specified in the README.

Limitations & Caveats

The project relies on external Azure APIs, which may incur costs. The README indicates a dependency on a separate backend repository for core functionality, requiring additional setup.