Bella is an AI-powered digital companion designed to offer personalized interaction and emotional connection. Targeting users seeking a sophisticated, evolving digital friend, Bella aims to transcend typical chatbot functionalities by integrating voice, visual, and emotional elements into a cohesive experience.

How It Works

Bella employs a modular, event-driven architecture with AI at its core. It utilizes Whisper ASR for voice perception, integrates with LLMs for dialogue, and supports TTS for speech synthesis. The system features a singleton BellaAI class for managing AI interactions and includes a basic affinity system for emotional feedback, aiming for natural, Siri-like conversations.

Quick Start & Requirements

• Install: Clone the repository, run npm install, npm run download (for AI models), and npm start.
• Requirements: Node.js 22.16.0+, modern browser with Web Speech API support, microphone permissions.
• Links: Project Repository, Product Requirements Document

Highlighted Details

• Enhanced LLM dialogue with optimized prompt engineering and parameter configuration for more natural conversations.
• Implements voice perception (Whisper ASR), visual expression (random video playback), and a responsive UI.
• Automatic AI model download and management.
• Modular design principles with AI as the central blueprint.

Maintenance & Community

The project is primarily developed by Grishma Mahorkar. Further community engagement details are not explicitly provided in the README.

Licensing & Compatibility

Licensed under the MIT License, permitting commercial use and integration with closed-source projects.

Limitations & Caveats

The project is currently in Alpha status, with planned features like a memory system, facial perception, and advanced interaction still under development. The core AI integration framework is ready, but TTS and emotional state systems are noted as "ready for activation" or "basic infrastructure built."