Journal of Computers, Mechanical and Management

PDF

Cite article

Rights and permissions

G. Jagtap, S. Jawalekar, M. Khandwe, Y. Khushalani, A. Kolhapure, V. Rajput, VISTA.AI: Voice-based interactive system for transformative assistance via holographic display, Journal of Information and Communications Technology: Algorithms, Systems and Applications, 2026, 2(1), 26302, doi: https://doi.org/10.64189/ict.26302.

Rights and permissions

© The Author(s) 2026.

Open Access

This article is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License, which permits the non-commercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as appropriate credit to the original author(s) and the source is given by providing a link to the Creative Commons License and changes need to be indicated if there are any. The images or other third-party material in this article are included in the article's Creative Commons License, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons License and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this License, visit: httpshttps://creativecommons.org/licenses/by-nc/4.0/

Abstract

The growing demand for intelligent automation has led to the rapid development of AI-powered assistants. However, these assistants have been limited to voice communication and working on a 2D screen. The main limitation of such systems exists at the level of user engagement. This paper introduces a model called VISTA.AI, a type of AI-powered assistive technology that overcomes all previous limitations in terms of functionality, uses voice commands for desktop operations, and designs hologram-ready visuals. The proposed system records voice commands through a microphone and processes them using natural language processing (NLP). The interpreted commands are then used to perform operating-system-level tasks.The model is designed using Blender-based modelling to generate extrusions and depth mapping. These elements are then used to create 2D visuals such as text, graphs, and icons, which are projected as 3D hologram-ready images. These frames are projected using a Pepper's Ghost setup, thereby creating floating holographic images. The experimental evaluation under controlled lighting conditions reveals high recognition accuracy, efficient automation of OS, and good-quality holographic outputs. VISTA.AI integrates multimodal interactions with OS-level control and low-cost holographic projection. This significantly enhances the capabilities of traditional AI assistants.Its modular architecture will allow gesture-based control, volumetric holography, integration into smart environments, and compatibility with AR/VR to be added in the future. This work presents a pathway toward the realization of Jarvis-like interfaces in a practical way by developing a scalable and reasonably priced framework that highlights immersive AI-driven human–computer interactions. Our results show that it is feasible to make use of accessible technologies to realize the synthesis of speech commands, automated system tasks, and 3D holographic visualization in real time, thus opening routes toward more immersive, interactive, and engaging computing experiences.

Keywords:

• Artificial intelligence
• Voice-based assistant
• Natural language processing
• Operating system automation
• Holographic display

Graphical Abstract

Novelty statement

A modular AI system integrating desktop control and real-time holographic projections for immersive, low-cost humancomputer interaction.