Interview Prep App

An in-progress local-first AI-powered mock interview app.
Users can upload their resume, choose their role, and configure the interview style.
The app generates context-aware questions (using your resume and previous answers), records your responses, and provides structured feedback.

🚧 Current Status

• Runs locally (due to Whisper API costs; offline options under exploration).
• Supports:
  • Uploading a resume for personalized question generation.
  • Choosing role and interview type (behavioral, technical, etc.).
  • Recording answers, with follow-up questions that adapt based on your responses.

✨ Planned Features

• 📊 Progress Tracking: View trends and improvements across multiple sessions.
• 🤖 Semantic Feedback: Automated scoring for professionalism and confidence.
• ⚡ Optimizations: Faster transcription and reduced response latency.
• 🖥️ UI Enhancements: Polished, distraction-free interface for realistic practice.
• 🔐 Extended Local Support: Explore open-source alternatives for transcription.

🛠️ Tech Stack

• Frontend: React + Next.js with TailwindCSS
• Backend: Python (FastAPI)
• LLM for Question Generation: Llama 3 (via Hugging Face)
• Transcription: Whisper

📂 Project Structure

interview\_prep\_app/
├── frontend/        # Next.js + TailwindCSS UI
├── backend/         # FastAPI backend
└── README.md        # Project documentation

🚀 Getting Started

Clone the repository:

git clone https://github.com/saltyquackerd/interview_prep_app.git
cd interview_prep_app

Frontend

cd frontend
npm install
npm run dev

Backend

cd backend
pip install -r requirements.txt
uvicorn main:app --reload

⚠️ Note: Some features (e.g. transcription) currently depend on external APIs. Local replacements are on the roadmap.

📌 Roadmap

• End-to-end mock interview flow (resume upload → adaptive Q&A → recording)
• Dashboard for performance tracking
• Semantic scoring (professionalism, confidence, clarity)
• Whisper optimizations / local transcription
• UI polish + deployment