International Journal For Multidisciplinary Research

E-ISSN: 2582-2160   •   Impact Factor: 9.24

A Widely Indexed Open Access Peer Reviewed Multidisciplinary Bi-monthly Scholarly International Journal

Call for Paper Volume 7, Issue 3 (May-June 2025) Submit your research before last 3 days of June to publish your research paper in the issue of May-June.
Submit Research Paper Join as a Reviewer

Plagiarism is checked by the leading plagiarism checker TurnItIn

Call for Paper

Volume 7 Issue 3
May-June 2025

Submit your research paper

Indexing Partners
Academia Advanced Sciences Index Bielefeld Academic Search Engine CiteSeer DRJI Google Scholar Independent Search Engine & Directory Network ISI (International Scientific Indexing) Issuu Mendeley Research Networks
RefSeek ResearcherId - Thomson Reuters ResearchGate Scirus Scribd Semantic Scholar UTeM - Universiti Teknikal Malaysia Melaka Wiki for Call for Papers WorldCat Zenodo

Conversational AI Video Assistant

Author(s) Mahammad Saadullah, Musrat Sultana, Dr. K. Rajitha, R. MohanKrishna Ayyappa
Country India
Abstract This research paper introduces a Conversational AI Video Assistant developed to enhance user interaction with video content through the processing of inputs, transcription of audio, analysis of scenes, and delivery of context-aware responses in near real-time. The system is equipped with Whisper for accurate audio transcription, custom object detection models built using OpenCV and TensorFlow for visual analysis, and Coqui TTS for natural-sounding audio feedback, all integrated seamlessly via a user-friendly Gradio-based interface. Extensive evaluation across multiple test videos demonstrates efficient performance, with processing times scaling linearly with video length and an average real-time factor of 0.173, confirming suitability for real-time applications. The system also exhibits robust effectiveness, achieving an overall accuracy of 0.86, precision of 0.83, recall of 0.88, and F1-score of 0.85, which reflects its reliability in delivering relevant responses. Designed for practical applications, the assistant supports diverse domains such as education—enabling interactive learning from instructional videos—accessibility, by providing audio descriptions for visually impaired users, and smart home systems, through contextual assistance. By combining multimodal processing with an intuitive interface, this Conversational AI Video Assistant provides a transformative solution for engaging with video content interactively and meaningfully.
Keywords Conversational AI, Video Analysis, Scene Understanding, Multimodal Interaction, User Experience
Field Computer > Artificial Intelligence / Simulation / Virtual Reality
Published In Volume 7, Issue 3, May-June 2025
Published On 2025-05-28
DOI https://doi.org/10.36948/ijfmr.2025.v07i03.46053
Short DOI https://doi.org/g9mn6f
View / Download PDF File

Share this



E-ISSN 2582-2160
CrossRef

CrossRef DOI is assigned to each research paper published in our journal.

IJFMR DOI prefix is
10.36948/ijfmr

Downloads
Research Paper Format Copyright Permission Form and Undertaking Form Cover Page Vol 7 Isu 3Cover Page Vol 7 Isu 2Cover Page Vol 7 Isu 1

All research papers published on this website are licensed under Creative Commons Attribution-ShareAlike 4.0 International License, and all rights belong to their respective authors/researchers.

CC-BY-SA Open Access

About IJFMR
Fees & Payment
Current Issue
Publication Archive 		Submit Research Paper
Track Submission Status
Publication Guidelines
Publication Ethics
Peer Review & Plagiarism 		Join as a Reviewer
Editors & Reviewers
Reviewer Referral Program
Get Reviewer Membership Certi. 		Website/Journal Policies
Usage Policy
Content Policies
Privacy Policy
Contact Us +91-9687-828-838 editor@ijfmr.com