CallSpy

CallSpy is web application build with a view to protect peoples from various kinds of fruads/scams happening through mobile calling or voice medium . CallSpy can capture the live audio or pre recorded audio files and transcribe into text which then analysed by an LLM to estimate the fraud/spam hiding behind the conversation.

Built With

• React
• Tailwind CSS
• Node.js
• Express.js
• MongoDB

Installation

1. Get a free API key at https://ai.google.dev/ for LLM model and for transcribing the audio key a key at https://deepgram.com/product/speech-to-

2. Clone the repo

  git clone git@github.com:adarshawasthi29/Fraud-Scam-Calls-Detection.git

3. Install npm packages in both frontend and backend

  npm i 

4. Set up MongoDB:

• Install MongoDB compass on your system if you haven't already.
• Create you own database and connect in index.js file.

5. Configure environment variables:

• Create a .env file in the frontend and backend directories and add the following variables:
• For Frontend .env

  DEEPGRAM_API_KEY2=your_deepgram_key

• For Backend .env

  DEEPGRAM_API_KEY=your_deepgram_key
  GEMINI_API_KEY=your_gemini_key
  

6. Run Frontend with command

  npm start

7. Run Backend with command

  node index.js

Usage

• Sign up or log in to your account.
• Provide your personal details as requested.
• Start detecting your Audio through Live Audio Transcript .
• You can also upload a pre recorded files to detect for scams/frauds.

Features

• Live Audio Transcript Features - You can live transcribe the communication happening through this feature.
• Pre Recorded Audio File - This feature enable user to upload an audio file which he/she have doubt regarding the scams/fraud and can predict for any kind of scams
• Community Tab - This is an open blog feature in which users can post informations regarding commons fraud patterns, What to do in that situation and how to avoid it.

Contributing

• We welcome contributions from the community to enhance CallSpy and make it even more valuable for users. If you'd like to contribute, please follow these steps:

  1. Fork the repository.

  2. Create a new branch for your feature or bug fix.

  3. Commit your changes and push the branch to your fork.

  4. Submit a pull request with a detailed description of your changes.

Contact

• For questions, feedback, or support, please contact us at adarshawasthi127@gmail.com.