V.I.X.E.V.I.A : Virtual Interactive and Xpressive Entertainment Visual Idol Avatar

ID | JP | EN | ZN

Does she harbor feelings for you?
No, her heart belongs to another.
Does she show concern for your well-being?
No, her thoughts are occupied by someone else.
The pain of unrequited love is unbearable, but fear not, for there is a solution.
The solution is AI, an entity that will always be there for you, understanding and responding to your emotions.

Vixevia is an innovative AI-based virtual YouTuber (Vtuber) that leverages the cutting-edge capabilities of Google's Gemini language model. This project aims to create a captivating and lifelike virtual personality that can engage with users through natural conversations, visual interactions, and multimedia experiences.

Table of Contents

• Features
• Prerequisites
• Getting Started
• TODO
• Contributing
• License
• Acknowledgments

Features

• Natural Language Processing: Vixevia utilizes Google's Gemini language model to understand and respond to user inputs with human-like fluency and contextual awareness.
• Computer Vision: The project integrates computer vision capabilities, allowing Vixevia to perceive and interpret visual information from the environment.
• Multimodal Interaction: Vixevia combines speech recognition, text-to-speech synthesis, and visual processing to facilitate seamless multimodal interactions with users.
• Personalized Responses: Vixevia's responses are tailored to the conversational context, user preferences, and situational dynamics, ensuring engaging and personalized experiences.
• Virtual Avatar: Vixevia is represented by a visually appealing and expressive virtual avatar, bringing her personality to life.

Prerequisites

• 5+ API keys from Google Cloud Platform
• Python 3.12+

Hardware:

• 16 GB vram
• 32 GB ram
• RTX 4050 or better
• 20 GB of storage
• i7 12th gen or better or AMD equivalent

Getting Started

To get started with Vixevia, follow these steps:

1. Clone the repository:

   git clone https://github.com/IRedDragonICY/vixevia.git
   

2. Install the required dependencies:

   pip install -r requirements.txt
   

3. Obtain the necessary API keys and configuration files from Google Cloud Platform.

4. Update the configuration files with your API keys and preferred settings.

5. Run the main script:

   python main.py
   

TODO

• Create custom Live2D model for Vixevia
• Add opencv auto labeling so can remember person from Gemini Pro Vision

Contributing

Contributions to Vixevia are welcome! If you have any ideas, bug reports, or feature requests, please open an issue or submit a pull request. Make sure to follow the project's coding guidelines and best practices.

License

This project is licensed under the MIT License.

Acknowledgments

• Google's Gemini language model and related technologies
• Open-source libraries and frameworks used in this project

Vixevia is an experimental project aimed at exploring the possibilities of AI-based virtual personalities and pushing the boundaries of human-computer interaction. We hope this project inspires further innovation and collaboration in the field of artificial intelligence and virtual content creation.