MirrorView 🪞

An AI-Powered Mock Interview Platform with Real-time Observation

English | 中文

---

📖 Introduction

MirrorView is an intelligent mock interview application designed to help job seekers improve their interview skills through realistic simulations and AI-driven feedback. It combines a desktop client (PyQt5) with a robust backend server (Flask) to deliver a seamless experience.

Key features include AI Interviewer interactions, Real-time Video Streaming, and a unique Observer Mode that allows mentors or peers to watch live interviews and provide guidance.

✨ Key Features

🤖 AI Mock Interview

• Personalized Questions: Generates tailored interview questions based on your job intention and resume.
• Voice Interaction: Supports speech-to-text input (offline fallback available) for natural conversation.
• Smart Feedback: Provides comprehensive AI analysis, scoring, and improvement suggestions after each session.

👀 Observer Mode (Mirror View)

• Live Streaming: Broadcast your interview session via RTMP to allowed observers.
• Real-time Transcript: Observers see the synchronized chat history as the interview progresses.
• Join via Code: Simple invite code system for mentors to join sessions securely.

👤 User Profile

• Resume Parsing: Automatically extracts skills and project experience from uploaded resumes.
• Job Intention Management: Set and update your target role and experience level.
• Interview History: Review past performance, scores, and detailed feedback at any time.

🛠️ Technology Stack

• Client: Python, PyQt5, OpenCV, SpeechRecognition, PyAudio
• Server: Flask, SQLAlchemy, OpenAI/LangChain (for AI logic)
• Streaming: RTMP (Real-Time Messaging Protocol), FFmpeg
• Database: SQLite (default), extensible to PostgreSQL/MySQL

🚀 Getting Started

Prerequisites

• Python 3.11
• FFmpeg (for video streaming)

Installation

1. Clone the repository

   git clone https://github.com/yourusername/MirrorView.git
   cd MirrorView

2. Install dependencies

   pip install -r requirements.txt

Running the Application

1. Start the Server

   python server/app.py

   The server will start at http://localhost:5001.

2. Start the Client

   python client/main.py

📸 Screenshots

(Add screenshots of Main Window, Interview Interface, and Observer View here)

🤝 贡献指南

Welcome to submit Pull Requests or Issues to help improve this project!

📄 License

This project is licensed under the MIT License - see the LICENSE file for details.