MOCKAI- A Personalized Voice-Interactive Interview Simulation System Using LLMS and Real-Time Speech Analytics

Abstract

The increasing competitiveness of the job market necessitates effective and scalable interview preparation mechanisms for candidates. Conventional mock interview methods often lack realism, adaptability, and personalized evaluation, limiting their effectiveness. This project presents MOCKAI, an innovative AI-powered mock interview platform designed to enhance interview readiness through intelligent, voice-interactive systems. MOCKAI addresses key limitations of traditional mock interviews by introducing realism, adaptability, and personalized feedback into the preparation process. The system leverages Large Language Models (LLMs), natural language processing, and real-time speech analytics to simulate authentic interview environments across multiple domains. MOCKAI dynamically generates role-specific and skill-based interview questions, records and transcribes candidate responses, and evaluates performance using advanced speech and language analysis techniques. By analyzing factors such as content relevance, clarity, confidence, fluency, and communication effectiveness, the platform delivers instant, personalized feedback to users. MOCKAI functions as a personal AI interview coach, enabling candidates to practice repeatedly in a low-pressure environment while receiving actionable insights for improvement. The platform adapts to individual performance levels, ensuring tailored interview experiences that align with real-world hiring standards. Its interactive and user-friendly design promotes accessibility and engagement, helping users build confidence and refine their communication skills. Through its AI-driven approach, MOCKAI significantly improves interview preparedness, reduces anxiety, and enhances overall candidate performance. By combining cutting-edge AI technologies with human-centered design principles, MOCKAI offers a scalable and effective solution for modern interview preparation, empowering candidates to succeed in real-world recruitment scenarios.

Introduction

The text highlights the growing importance of interview performance in today’s competitive job market, where communication skills and response quality often outweigh technical knowledge. Many candidates fail interviews due to poor confidence, unclear answers, and lack of structured responses, while traditional preparation methods (like mock interviews or question banks) are limited, inconsistent, and not scalable.

To address these challenges, the proposed system, MOCKAI, is an AI-powered, voice-interactive mock interview platform. It uses advanced technologies such as Large Language Models (LLMs), Natural Language Processing (NLP), and speech analytics to generate dynamic, domain-specific interview questions and evaluate candidate responses in real time. The system assesses both content quality and communication aspects like clarity, fluency, and confidence, providing instant, personalized feedback.

MOCKAI functions as a scalable personal interview coach, allowing users to practice anytime with adaptive difficulty levels and realistic interview simulations. It also stores performance data and provides analytics dashboards for tracking progress over time. Compared to traditional methods, it improves response quality, boosts confidence, and reduces preparation time.

Conclusion

The MOCKAI- A personalized voice-conversational mock interview simulation system utilizing Large Language Models and real-time speech analyticsfor improved interview preparation. The system effectively overcomes the shortcomings of conventional mock interview approaches, including the absence of personalization, delayed feedback, and human evaluation [6] . By integrating adaptive question generation using LLMs, real-time speech interaction, and automatic evaluation, MOCKAI simulates a realistic and scalable environment for interview practice [20]. The developed system showcases the effective integration of contemporary web technologies and AI capabilities.The application of Next.js and Tailwind CSS facilitates a user-friendly and responsive interface, with Node.jshandling backend functionality.Supabaseservicesprovide secure user management and performance tracking [22]. Whisper AI automation enables seamless integration of speech input, transcription, AI evaluation, and feedback generation. In summary, MOCKAI serves as a virtual AI interview tutor, filling the existing gap between traditional interview preparation strategies and AI-powered intelligent evaluation systems [15]. This study makes a significant addition to the emerging field of AI-supported learning and professional development, providing an accessible, adaptive, and user-friendly interview preparation platform.

References

[1] C. Chou, F. R. Wongso, C. -Y. Chao and H. -Y. Yu, \"An AI Mock-interview Platform for Interview Performance Analysis,\" 2022 10th International Conference on Information and Education Technology (ICIET), 10.1109/ICIET55102.2022.9778999. [2] T. Sharma, A. Singh, S. Singh and G. Gupta, \"AI-Powered Mock Interview Platform using Computer Vision, Natural Language Processing and Generative AI,\" 2025 3rd International Conference on Self Sustainable Artificial Intelligence Systems (ICSSAS), Erode, India, 2025, pp. 1258-1263, doi: 10.1109/ICSSAS66150.2025.11080941. [3] P. K. Mishra, A. K. Arulappan, I. -H. Ra, T. M. L, G. R. G and Y. -S. Lee, \"AI-Driven Virtual Mock Interview Development,\" 2024 Joint 13th International Conference on Soft Computing and Intelligent Systems and 25th International Symposium on Advanced Intelligent Systems (SCIS&ISIS), Himeji, Japan, 2024, pp. 1-4, doi: 10.1109/SCISISIS61014.2024.10760210. [4] N. Amarasena, S. C. Rathnayaka, S. Fernando, T. Deiyagala, H. Biyon and N. Chandrasiri, \"Enhancing Employability Through an Advanced Mock Interview Platform for Fresh IT Graduates,\" 2024 7th International Seminar on Research of Information Technology and Intelligent Systems (ISRITI), Yogyakarta, 10.1109/ISRITI64779.2024.10963436. [5] B. Jadhav, A. Sawant, A. Shah, P. Vemula, A. Waikar and S. Yadav, \"A Comprehensive Study and Implementation of the Mock Interview Simulator with AI and Pose-Based Interaction,\" 2024 1st International Conference on Cognitive, Green and Ubiquitous Computing (IC-CGU), Bhubaneswar, India, 2024, pp. 01-05, doi: 10.1109/IC-CGU58078.2024.10530717. [6] R. Mandal, P. Lohar, D. Patil, A. Patil and S. Wagh, \"AI -Based mock interview evaluator: An emotion and confidence classifier model,\" 2023 International Conference on Intelligent Systems for Communication, IoT and Security (ICISCoIS), Coimbatore, India, 2023, pp. 521-526, doi: 10.1109/ICISCoIS56541.2023.10100589. [7] J. M. C J, M. Sabi, M. Benson, G. Baburaj and S. S, \"Q&AI: An AI Powered Mock Interview Bot for Enhancing the Performance of Aspiring Professionals,\" 2024 International Conference on Recent Advances in Electrical, Electronics, Ubiquitous Communication, and Computational Intelligence (RAEEUCCI), 1-5, doi:Chennai, 10.1109/RAEEUCCI61380.2024.10547951. [8] J. V. Barpute, O. Wattamwar, S. Pakjade and S. Diwate, \"A Survey of AI-Driven Mock Interviews Using GenAI and Machine Learning (InterviewX),\" 2024 4th International Conference on Ubiquitous Computing and Intelligent Information Systems (ICUIS), Gobichettipalayam, India, 2024, pp. 217-224, doi: 10.1109/ICUIS64676.2024.10866631. [9] R. A. M, A. R and V. P, \"InterviewIQ: AI-Powered Chatbot for Upskilling Candidates in Technical and HR Interviews,\" 2025 International Conference on Intelligent Control, Computing and Communications (IC3), 392-397, doi:Mathura, India, 2025, pp. 10.1109/IC363308.2025.10956589. [10] S. Chandrappa et al., \"SYNCHRON AI: Multiple Assistant Ai Chatbot-Personalized Exam Prep Ecosystem,\" 2025 5th International Conference on Intelligent Technologies (CONIT), HUBBALI, India, 2025, pp. 1-7, doi: 10.1109/CONIT65521.2025.11167432. [11] R. Islam and I. Ahmed, \"Gemini-the most powerful LLM: Myth or Truth,\" 2024 5th Information Communication Technologies Conference (ICTC), Nanjing, China, 2024, pp. 303-308, doi: 10.1109/ICTC61510.2024.10602253. [12] R. Umbare, A. Budhodkar, S. Suryawanshi, S. Udgirkar, P. Aher and S. Rangdale, \"From Practice to Perfection: AI-Driven Mock Interviews for Career Success,\" 2024 International Conference on Sustainable Communication Networks and Application (ICSCNA), Theni, India, 2024, pp. 1250-1257, doi: 10.1109/ICSCNA63714.2024.10864324. [13] A. Nagpure, R. Kharat and T. Deotale, \"AI Driven Virtual Interview Platform,\" 2025 IEEE International Conference on Advanced Computing Technologies (ICACT), Tirupati, India, 2025, pp. 100-105, doi: 10.1109/ICACT67549.2025.11351461. [14] S. K, A. M, D. R and M. S, \"AI-Powered Virtual Interview System: An Intelligent Approach to Automated Candidate Assessment Using NLP and Machine Learning,\" 2025 9th International Conference on Inventive Systems and Control (ICISC), Coimbatore, India, 2025, pp. 78-81, doi: 10.1109/ICISC65841.2025.11188384. [15] N. Boudjani, V. Colas, C. Joubert and D. B. Amor, \"AI Chatbot For Job Interview,\" 2023 46th MIPRO ICT and Electronics Convention (MIPRO), Opatija, Croatia, 2023, pp. 1155-1160, doi: 10.23919/MIPRO57284.2023.10159831. [16] G. S. Rao, M. Jaiganesh, M. A. K, M. A. A. A, N. R and P. K. Parida, \"AI Powered Virtual Job Interview Simulator Using Natural Language Processing,\" 2025 8th International Conference on Trends in Electronics and Informatics (ICOEI), Tirunelveli, India, 2025, pp. 1413-1421, doi: 10.1109/ICOEI65986.2025.11013504. [17] S. Sarumathi, G. R. L, S. M. B and S. A, \"AI-Enhanced HR Interview Simulation for Realistic Candidate Assessment,\" 2025 3rd International Conference on Intelligent Data Communication Technologies and Internet of Things (IDCIoT), Bengaluru, India, 2025, pp. 1089-1095, doi: 10.1109/IDCIOT64235.2025.10915193. [18] N. LAHIANI and A. MERZOUG, \"An Intelligent Multilingual Legal Chatbot for Algerian Law Based on RAG and LLMs,\" 2025 International Conference on Intelligent Computer Systems, Data Science and Applications (IC2SDA), Blida, Algeria, 2025, pp. 1-5, doi: 10.1109/IC2SDA68097.2025.11331471. [19] C. Raghavendra, P. Nagarani and R. S. Rani, \"Speech Emotion Recognition: Node.js and Web Speech API,\" 2022 International Conference on Computer, Power and Communications (ICCPC), Chennai, India, 2022, pp. 439-445, doi: 10.1109/ICCPC55978.2022.10072048. [20] P. V. K. V. Prasad, N. V. Krishna and T. P. Jacob, \"AI CHATBOT using Web Speech API and Node.Js,\" 2022 International Conference on Sustainable Computing and Data Communication Systems (ICSCDS), Erode, India, 2022, pp. 360-362, doi: 10.1109/ICSCDS53736.2022.9760803. [21] J. Choi, H. Gill, S. Ou, Y. Song and J. Lee, \"Design of Voice to Text Conversion and Management Program Based on Google Cloud Speech API,\" 2018 International Conference on Computational Science and Computational Intelligence (CSCI), Las Vegas, NV, USA, 2018, pp. 1452-1453, doi: 10.1109/CSCI46756.2018.00286. [22] S. Singh Rauthan, N. Rathore, Y. Kumar, Y. Kumar Singh and D. Birari, \"Emotion Detection Using Speech and Text Recognition: An Overview,\" 2023 International Conference on Data Science and Network Security (ICDSNS), Tiptur, India,2023, pp.1-5, doi: 10.1109/ICDSNS58469.2023.10245618. [23] P. M. ee, S. Santra, S. Bhowmick, A. Paul, P. Chatterjee and A. Deyasi, \"Development of GUI for Text-to-Speech Recognition using Natural Language Processing,\" 2018 2nd International Conference on Electronics, Materials Engineering & Nano-Technology (IEMENTech), Kolkata, India, 2018, pp. 1-4, doi: 10.1109/IEMENTECH.2018.8465238. [24] K. Subramani, S. T, V. K, C. K, A. D and D. V, \"Leveraging AI and PostgreSQL for an Inclusive Neurodivergent Career Platform,\" 2025 4th International Conference on Applied Artificial Intelligence and Computing (ICAAIC), Salem, India, 2025, pp. 1611-1619, doi: 10.1109/ICAAIC64647.2025.11330970

Copyright

Copyright © 2026 Yutika Satish Kumbhar, Yogita Ravindra Khade, Anushka Nitin Jagtap, Janisa Pereira . This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.