CoolFace
Apppublic

siddheshgawade11/AI-Generated-Voice-Detection

sourceHugging Faceupdated 8mo agoView on Hugging Face
0likes
App README

VocalGuard AI - Voice Detection System

<div align="center">

VocalGuard AI React Tailwind CSS FastAPI

Advanced Deepfake Audio Detection with Real-time Analysis

Live Demo · Report Bug · Request Feature

</div>

🚀 About The Project

VocalGuard AI is a production-grade system designed to detect AI-generated voices in audio files with high accuracy. Built for the GUVI HCL India AI Impact Buildathon, it combines a robust backend API with a modern, user-friendly frontend to verify digital audio authenticity.

✨ Key Features

  • —99.2% Detection Accuracy: Powered by Wav2Vec2 embeddings and neural nertwork classifiers.
  • —Real-time Analysis: Get instant verdicts (Authentic vs. AI Generated) with detailed confidence scores.
  • —Multi-language Support: Optimized for Tamil, English, Hindi, Malayalam, and Telugu.
  • —Modern UI/UX:
  • —Light Theme: Clean, professional design with vibrant pink/magenta accents.
  • —Visual Analytics: Circular confidence meters and interactive result cards.
  • —Responsive: Fully optimized for mobile and desktop devices.
  • —Secure: API Key authentication with local storage persistence for seamless usage.

🛠️ Technology Stack

Frontend

  • —Framework: React (Vite)
  • —Styling: Tailwind CSS v4 (with custom animations & gradients)
  • —State/Logic: Framer Motion, Axios
  • —Icons: Lucide React

Backend

  • —Core: Python 3.11+, FastAPI
  • —ML Engine: PyTorch, Wav2Vec2, Librosa
  • —Processing: FFmpeg for audio conversion
  • —Containerization: Docker

🏁 Getting Started

Prerequisites

  • —Node.js 18+
  • —Python 3.11+
  • —FFmpeg (for local backend)

1. Clone the Repository

bash
git clone https://github.com/yourusername/vocalguard.git
cd vocalguard

2. Frontend Setup

bash
cd frontend
npm install
npm run dev

The app will launch at http://localhost:5173.

3. Backend Setup (Optional)

If you want to run the backend locally instead of using the hosted API:

bash
cd .. # Go back to root
python -m venv venv
source venv/bin/activate  # or venv\Scripts\activate on Windows
pip install -r requirements.txt
python app.py

The API will run at http://localhost:8000.

🔌 API Documentation

Endpoint: POST /api/voice-detection

Headers:

  • —x-api-key: YOUR_SECRET_KEY
  • —Content-Type: application/json

Body:

json
{
  "language": "English",
  "audioFormat": "mp3",
  "audioBase64": "<BASE64_STRING>"
}

Response:

json
{
  "status": "success",
  "classification": "AI_GENERATED",
  "confidenceScore": 0.98,
  "explanation": "High spectral uniformity detected..."
}

📸 Screenshots

Landing PageAnalysis Result
[Add Screenshot Here][Add Screenshot Here]

🤝 Contributing

Contributions are what make the open source community such an amazing place to learn, inspire, and create. Any contributions you make are greatly appreciated.

  1. 1.Fork the Project
  2. 2.Create your Feature Branch (git checkout -b feature/AmazingFeature)
  3. 3.Commit your Changes (git commit -m 'Add some AmazingFeature')
  4. 4.Push to the Branch (git push origin feature/AmazingFeature)
  5. 5.Open a Pull Request

📄 License

Distributed under the MIT License. See LICENSE for more information.

<div align="center"> Built with ❤️ for a safer digital future. </div>