🎯 Interview Assistant

An AI-powered desktop application that helps you prepare for interviews by capturing voice questions and generating personalized, perfect answers using OpenAI's GPT-4o.

✨ Features

• 🎤 Voice Recording: Capture interview questions with high-quality audio
• 🤖 AI-Powered Answers: Generate personalized responses using GPT-4o
• 📄 Resume Integration: Tailor answers based on your actual experience and skills
• 🔊 Text-to-Speech: Listen to generated answers with natural voice synthesis
• 💾 Profile Management: Store and manage your resume data
• 🖥️ Desktop App: Cross-platform Electron application

🛠️ Tech Stack

• Frontend: React + Tailwind CSS + Electron
• Backend: Node.js + Express
• AI Services: OpenAI (Whisper, GPT-4o, TTS)
• Audio Processing: Web Audio API + MediaRecorder

🚀 Quick Start

Prerequisites

• Node.js (v16 or higher)
• npm or yarn
• key here

Installation

1. Clone and install dependencies:

   npm install

2. Set up environment variables:

   cp env.example .env

   Edit .env and add your key here:

   OPENAI_API_KEY=your_openai_api_key_here
   

3. Start the development server:

   npm run dev

   This will start both the backend server (port 5000) and the Electron app.

Alternative: Run components separately

• Backend only: npm run server
• Frontend only: npm start
• Electron only: npm run electron-dev

📱 Usage

1. Set up your profile: Go to "Resume Manager" and fill in your experience, skills, projects, and achievements.

2. Record questions: Use the voice recorder to capture interview questions. The app will automatically transcribe them using Whisper.

3. Generate answers: Click "Generate Perfect Answer" to get a personalized response using GPT-4o.

4. Listen to answers: Use the text-to-speech feature to hear your answers spoken aloud.

🔧 Configuration

Audio Settings

• Microphone permissions are required for voice recording
• Audio quality: 44.1kHz, Opus codec
• Noise suppression and echo cancellation enabled

AI Configuration

• Speech-to-Text: OpenAI Whisper API
• Answer Generation: GPT-4o with custom prompts
• Text-to-Speech: OpenAI TTS (Nova voice)

📦 Building for Production

# Build the React app
npm run build

# Package the Electron app
npm run electron-pack

The built application will be in the dist folder.

🔒 Security Notes

• API keys are stored in environment variables
• Audio data is processed locally and sent to OpenAI for transcription
• Resume data is stored locally (consider database for production)

🤝 Contributing

1. Fork the repository
2. Create a feature branch
3. Make your changes
4. Test thoroughly
5. Submit a pull request

📄 License

MIT License - see LICENSE file for details.

🆘 Troubleshooting

Common Issues

Microphone not working:

• Check browser/system permissions
• Ensure microphone is not being used by another application

OpenAI API errors:

• Verify your API key is correct
• Check your OpenAI account has sufficient credits
• Ensure you have access to GPT-4o and Whisper APIs

Audio transcription issues:

• Speak clearly and reduce background noise
• Check internet connection
• Verify audio file size is under 25MB

Getting Help

• Check the console for error messages
• Ensure all dependencies are installed
• Verify environment variables are set correctly

🔮 Future Enhancements

• Support for multiple languages
• Interview question database
• Practice session analytics
• Integration with calendar apps
• Mock interview scheduling
• Answer customization options
• Export functionality for answers

---

Happy interviewing! 🎉