TalentScope AI

AI-powered recruitment platform for smarter hiring decisions

TalentScope AI is an AI-powered recruitment and interview analysis platform designed to help recruiters identify the best candidates and assist candidates in improving their interview performance.

---

Overview

TalentScope AI combines machine learning, NLP, and video analysis to evaluate candidates across multiple dimensions:

• Facial emotion detection

• Speech and tone analysis

• Sentiment analysis

• Resume-to-job matching

• Recruiter analytics dashboard

---

Features

Recruiter

• Create and manage job postings

• View applicants and filter candidates

• Analyze interview performance

• Access detailed analytics and reports

• Schedule interviews

Candidate

• Browse and apply for jobs

• Upload resume

• Attend video interviews

• Practice interviews with AI feedback

• View performance analysis

---

Screenshots

🔹 Home Page

🔹 Recruiter Dashboard

🔹 Candidate Dashboard

🔹 Interview Analysis

---

Tech Stack

🔹 Frontend

• React (Vite)

• Redux Toolkit

• Tailwind CSS

• Axios

🔹 Backend

• Flask

• MongoDB (PyMongo)

• JWT Authentication

🔹 AI / ML

• DeepFace (emotion detection)

• Transformers (sentiment analysis)

• SpeechRecognition (STT)

• Parselmouth (speech prosody)

• Scikit-learn (resume matching)

---

Project Structure

TalentScope-AI/

│

├── backend/

│ ├── app/

│ ├── routes/

│ ├── models/

│ ├── services/

│ └── utils/

│

├── frontend/

│ ├── src/

│ │ ├── components/

│ │ ├── features/

│ │ ├── pages/

│ │ ├── redux/

│ │ └── api/

│

└── README.md

---

Setup Instructions

🔹 1. Clone Repository

git clone https://github.com/vipulsystems/talentscope-ai.git

cd talentscope-ai

---

🔹 2. Backend Setup

cd backend

python -m venv venv

venv\Scripts\activate # Windows

# source venv/bin/activate # Mac/Linux

pip install -r requirements.txt

Create .env file:

MONGO_URI=mongodb://localhost:27017/interview_db

JWT_SECRET_KEY=your_secret_key

SECRET_KEY=your_secret_key

FLASK_ENV=development

Run backend:

flask run

Backend runs at:

http://127.0.0.1:5000

---

🔹 3. Frontend Setup

cd frontend

npm install

Create .env file:

VITE_API_URL=http://127.0.0.1:5000

Run frontend:

npm run dev

Frontend runs at:

http://localhost:5173

---

Authentication

• JWT-based authentication

• Role-based access:

• Candidate

• Recruiter

---

API Base URL

http://127.0.0.1:5000/api/v1

---

Example Features in Action

• Upload resume → get similarity score

• Upload interview video → get:

• emotion score

• speech score

• sentiment score

• Recruiter sees:

• overall candidate score

• recommendation (Strong Fit / Needs Review)

---

Future Enhancements

• Live interview (WebRTC)

• AI question generation

• Resume parser improvements

• Candidate ranking system

• Deployment (Docker + Cloud)

---

Author

Built by Vipul Paighan

---

License

This project is licensed under the MIT License.

---

TalentScope AI — Smarter Hiring with AI