Home / Current Issue / Paper 1716017
PrepTalk – Applicant Selector AI
Subject area: Science,Engineering and Technology · Area of research: Artificial Intelligence
DOI: 10.64388/IREV9I10-1716017
Abstract
In today’s competitive hiring landscape, candidates often struggle to access realistic, structured interview practice, while recruiters face challenges in maintaining consistency, fair- ness, and efficiency in evaluation. PrepTalk – Applicant Selector AI is a hybrid Full Stack + AI interview simulation platform that provides a real-time, boardroom-like mock interview experience using webcam, microphone, and intelligent feedback mechanisms. The system dynamically generates role-specific technical and non- technical questions using the Gemini API based on job role, tech stack, and experience, and evaluates candidate responses through AI-driven analysis of recorded audio (speech-to-text) and stored transcripts. The platform integrates an enhanced speech recognition module with a Drizzle ORM–backed Post- greSQL database to securely store questions, answers, feedback, ratings, and past interview sessions for continuous review and improvement. Users can log in, configure their job profile, start a mock interview, record answers in real time, and finally receive structured feedback that includes ideal answers, detailed improvement suggestions, and an overall performance score. By automating question generation, response evaluation, and feedback delivery, PrepTalk reduces manual effort, improves con- sistency and fairness, and offers an accessible, scalable solution for candidates preparing for campus placements and professional interviews.
Keywords
AI Mock Interview, Gemini API, Speech Recog- nition, Full Stack Application, Drizzle ORM, PostgreSQL, Inter- view Simulation, Automated Feedback, Applicant Assessment, Web-based Interview Platform
References
[1] S. Banerjee and T. Mukherjee, “AI-assisted Interview Systems: A Re- view of Methods and Applications,” International Journal of Computer Science and Information Security (IJCSIS), 2021.
[2] K. R. Patel and A. Mehta, “Digital Hiring and Automated Candidate Screening: A Comprehensive Overview,” Journal of Contemporary Management Research, 2020.
[3] L. Zhang and Q. Li, “Machine Learning Models for Candidate Evaluation and Scoring in Recruitment Systems,” International Journal of Business Information Systems, 2019.
[4] M. Ahmed and S. Khan, “Role of Analytics in Modern Recruitment and Performance Assessment,” International Journal of Interactive Mobile Technologies (iJIM), 2022.
[5] J. Chen et al., “AI-driven Interview Question Generation Using Large Language Models,” arXiv preprint arXiv:2305.01234, 2023.
[6] R. Wilson and T. Carter, “Factors Influencing Candidate Experience in Digital Recruitment Platforms,” International Journal of Research in Computer Science and Management, 2021.
[7] P. Singh, “Economic Impact of AI-based Hiring Systems in Emerging Job Markets,” ShodhKosh, 2022.
[8] M. S. Raj et al., “Improving Recruitment Efficiency through Automated Screening and Scoring,” International Journal of Business and Management Practices (IJBMP), 2020.
[9] A. Das, “Sentiment and Expression Analysis for Behavioral Evaluation in AI Interviews,” arXiv preprint arXiv:2209.01876, 2022.
[10] Y. Wang et al., “Fairness and Bias Challenges in AI-assisted Candidate Selection,” arXiv preprint arXiv:2301.04562, 2023.
[11] S. Lee et al., “Natural Language Processing Techniques for Interview Transcript Analysis,” arXiv preprint arXiv:2108.07789, 2021.
[12] P. George et al., “Performance Evaluation of Online Interview Assessment Platforms,” Asian Journal of Research in Computer Science (AJRCS), 2022.
[13] R. Omar and B. Ali, “Emerging Trends in AI-driven Recruitment and Talent Management,” International Journal of Information Technology and Computer Engineering, 2023. Asian Journal of Research in Computer Science (AJRCS).
How to cite this paper
@article{1716017,
author = {Deepak S, Yeswant B.V., T. Rajesh},
title = {PrepTalk – Applicant Selector AI},
journal = {Iconic Research And Engineering Journals},
year = {2026},
volume = {9},
number = {10},
pages = {598-604},
issn = {2456-8880},
url = {https://www.irejournals.com/formatedpaper/1716017.pdf},
abstract = {In today’s competitive hiring landscape, candidates often struggle to access realistic, structured interview practice, while recruiters face challenges in maintaining consistency, fair- ness, and efficiency in evaluation. PrepTalk – Applicant Selector AI is a hybrid Full Stack + AI interview simulation platform that provides a real-time, boardroom-like mock interview experience using webcam, microphone, and intelligent feedback mechanisms. The system dynamically generates role-specific technical and non- technical questions using the Gemini API based on job role, tech stack, and experience, and evaluates candidate responses through AI-driven analysis of recorded audio (speech-to-text) and stored transcripts. The platform integrates an enhanced speech recognition module with a Drizzle ORM–backed Post- greSQL database to securely store questions, answers, feedback, ratings, and past interview sessions for continuous review and improvement. Users can log in, configure their job profile, start a mock interview, record answers in real time, and finally receive structured feedback that includes ideal answers, detailed improvement suggestions, and an overall performance score. By automating question generation, response evaluation, and feedback delivery, PrepTalk reduces manual effort, improves con- sistency and fairness, and offers an accessible, scalable solution for candidates preparing for campus placements and professional interviews.},
keywords = {AI Mock Interview, Gemini API, Speech Recog- nition, Full Stack Application, Drizzle ORM, PostgreSQL, Inter- view Simulation, Automated Feedback, Applicant Assessment, Web-based Interview Platform},
month = {April},
doi = {https://doi.org/10.64388/IREV9I10-1716017}
}