Copyright © 2026 Authors retain the copyright of this article. This article 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.

@article{201309,
        author = {Parupally Chandana and N.V. Sravan kumar and Nikhil S Kallakuri and Ch. Raja},
        title = {RoboPi: A Fully Offline Voice-Interactive Desktop Companion Robot.},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {12},
        pages = {3442-3449},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=201309},
        abstract = {This paper presents RoboPi, a fully offline voice-interactive AI companion robot developed using Raspberry Pi 5. The system is designed to provide natural human-like interaction without relying on cloud services, ensuring complete data privacy. RoboPi integrates advanced technologies including local large language models (LLMs) using Ollama, speech recognition through Whisper, and voice synthesis using Piper TTS. The system also features a visual feedback mechanism through a TFT display that shows real-time facial expressions based on interaction states. The robot is capable of understanding voice commands, generating contextual responses, and expressing emotions through a multi-modal interface. The implementation demonstrates that advanced AI functionalities can be efficiently executed on resource-constrained hardware. RoboPi can be used as a personal assistant, educational tool, or smart home interface. The project highlights the potential of embedded AI systems in creating intelligent and privacy-focused applications.},
        keywords = {Offline AI, Voice Assistant, Raspberry Pi, Embedded Systems, Local LLM, Human-Computer Interaction.},
        month = {May},
        }