An AI-powered mock interview application that provides an interactive interview experience using voice input, speech recognition, AI-generated responses, role selection, and automated evaluation with feedback.
The AI Mock Interview Simulator is a Python-based application designed to simulate an interview environment for users preparing for technical and professional interviews.
The application provides an interactive interview session where users can select an interview role, answer questions using voice input, and receive an evaluation and feedback at the end of the interview.
The project combines speech recognition, AI language models, and a graphical user interface to create an interactive mock interview experience.
- 🎤 Voice-based interview interaction
- 🗣️ Speech-to-text processing
- 🤖 AI-powered interview experience
- 👨💼 Role-based interview selection
- 💬 Interactive interview questions and answers
- 📝 Automated interview evaluation
- 📊 Evaluation score and feedback
- 🔄 Follow-up questions during the interview
- 🖥️ Graphical User Interface
- 🎧 Microphone and audio input support
- 🏠 Local model-based processing
- Python
- Tkinter
- Vosk
- GPT4All
- pip
- Desktop application
- Local AI application
- Voice-enabled application
Tkinter is used to provide the graphical user interface for the application.
The interface allows users to:
- Select an interview role
- Start an interview
- Enter or provide answers
- Start and stop voice recording
- View the interview interaction
- Receive evaluation and feedback
Vosk is used for speech recognition and converting microphone input into text.
The application uses Vosk to support voice-based answers during the interview.
GPT4All is used as the local AI language-model component of the application.
The language model is used to support the interview interaction and generate AI-based responses.
┌───────────────────────┐
│ User │
└───────────┬───────────┘
│
▼
┌───────────────────────┐
│ Tkinter GUI │
│ │
│ Role Selection │
│ Interview Interface │
│ Recording Controls │
└───────────┬───────────┘
│
┌───────────┴───────────┐
│ │
▼ ▼
┌─────────────────┐ ┌─────────────────┐
│ Microphone │ │ GPT4All │
│ Audio Input │ │ Language Model │
└────────┬────────┘ └────────┬────────┘
│ │
▼ │
┌─────────────────┐ │
│ Vosk │ │
│ Speech-to-Text │ │
└────────┬────────┘ │
│ │
└───────────┬───────────┘
▼
┌───────────────────────┐
│ Interview Processing │
└───────────┬───────────┘
│
▼
┌───────────────────────┐
│ Evaluation & Feedback │
└───────────────────────┘
AI-MOCK-INTERVIEW-SIMULATOR/
│
├── main.py
├── README.md
├── REPORT.pdf
├── PPT.pptx
├── AI MOCK INTERVIEW SIMULATOR OUTPUT.docx
├── How_to_Run_AI_Mock_Interview_Simulator.docx
└── model/
The project requires:
- Python 3.8 or above
- Windows, Linux, or macOS
- Microphone/audio input
- Python package manager (
pip) - Vosk speech-recognition model
- GPT4All-compatible language model
git clone https://github.com/raghish/AI-MOCK-INTERVIEW-SIMULATOR.git
cd AI-MOCK-INTERVIEW-SIMULATORInstall the required dependencies using:
pip install -r requirements.txtIf a requirements.txt file is not available in your local copy, install the required packages according to the project configuration.
The application uses a Vosk speech-recognition model for converting microphone audio into text.
Download the required Vosk model and place it inside the project directory using the model folder expected by the application.
Example structure:
AI-MOCK-INTERVIEW-SIMULATOR/
│
├── main.py
├── model/
│ └── Vosk Model Files
│
└── README.md
The Vosk model must be available locally before starting the application.
The application uses a GPT4All-compatible language model for AI-powered interview functionality.
Download the required model and place it inside the project directory using the model folder expected by the application.
Example:
model/
└── GPT4All Model
The required model must be downloaded before running the application.
Navigate to the project directory:
cd AI-MOCK-INTERVIEW-SIMULATORRun the application:
python main.pyThe application will open the graphical user interface.
Run:
python main.pyThe application opens a GUI window.
Select the required role, such as:
- Data Analyst
- Software Developer
- Other available roles
Select the option to start the interview.
The application begins the interview interaction.
Answers can be provided through the available input/voice interaction.
For voice input:
- Start recording
- Speak your answer
- Stop recording when finished
The application uses Vosk to convert the recorded speech into text.
The application uses GPT4All to support the interview interaction and generate AI-based responses.
The AI interviewer can continue the interview with follow-up questions.
At the end of the interview, the application provides an evaluation score and feedback.
The application provides an evaluation stage after the interview.
The evaluation includes:
- Interview performance assessment
- Evaluation score
- Feedback
- Follow-up interaction during the interview
This allows users to understand their performance and identify areas for improvement.
Launch Application
│
▼
Select Interview Role
│
▼
Start Interview
│
▼
Receive Interview Question
│
▼
Provide Answer
│
▼
Voice Input
│
▼
Vosk Speech Recognition
│
▼
Convert Speech to Text
│
▼
GPT4All AI Processing
│
▼
Follow-up Question
│
▼
Continue Interview
│
▼
Interview Completed
│
▼
Evaluation & Feedback
The application supports microphone-based interaction.
The basic voice workflow is:
Microphone
│
▼
Audio Input
│
▼
Vosk
│
▼
Speech-to-Text
│
▼
Interview Answer
Make sure the system microphone is working correctly before starting a voice-based interview.
GPT4All provides the language-model component used by the application.
The AI component supports:
- Interview interaction
- Question-and-answer flow
- Follow-up questions
- AI-generated responses
- Interview evaluation support
This project is designed to run locally.
The main application is started using:
python main.pyThe application requires the necessary AI and speech-recognition models to be available locally.
The project uses local AI and speech-processing components.
For safe usage:
- Do not store sensitive personal information in the repository.
- Do not upload private interview recordings.
- Do not commit private credentials or API keys.
- Keep downloaded model files and personal data outside the repository when appropriate.
This project demonstrates practical experience with:
- Python application development
- Tkinter GUI development
- Speech recognition
- Voice-based application development
- Natural language processing
- Local AI model integration
- GPT4All
- Vosk
- Microphone/audio processing
- Interactive application workflows
- AI-assisted interview evaluation
- User interface design
The main goals of the project are to:
- Provide an interactive mock interview environment
- Enable voice-based interview interaction
- Use speech recognition for spoken answers
- Integrate a local AI language model
- Simulate role-based interviews
- Provide interview evaluation and feedback
- Help users practice interview communication and responses
Potential future improvements include:
- More interview roles
- Improved interview evaluation
- More detailed performance analytics
- Additional language-model support
- Enhanced user interface
- Interview history and progress tracking
- Additional speech-processing capabilities
Additional project documentation is available in the repository, including:
- Project report
- Project presentation
- Project output documentation
- Project run instructions
Raghish S
B.Tech — Artificial Intelligence and Machine Learning
K. Ramakrishnan College of Technology
2022 – 2026
- GitHub: https://github.com/raghish
- LinkedIn: https://www.linkedin.com/in/raghish-s-a359a3257/
- Email: raghish2004@gmail.com
AI Mock Interview Simulator
An AI-powered desktop application combining:
Python • Speech Recognition • Local AI • Voice Interaction • Interview Simulation