Abstract
ZENO is an AI-powered voice assistant engineered as a standalone, interactive system capable of delivering intelligent, human-like conversations on embedded platforms. Developed using a Raspberry Pi and implemented in Python, ZENO seamlessly combines Speech-to-Text conversion using Google Speech Recognition, natural language response generation via LLaMA 3 70B hosted on Groq, and Text-to-Speech synthesis powered by Wit.ai. The system operates entirely in a headless mode, eliminating the need for a graphical interface and making it especially suitable for space-constrained or screen-less environments. Unlike traditional digital assistants [1], [2], ZENO offers a hybrid edge-cloud architecture that ensures both low-latency responsiveness and cloud-scale intelligence. Its modular design emphasizes simplicity, scalability, and emotional relatability, making it adaptable for use cases such as personal task management, elderly assistance [13], [14], and smart home automation [8], [11]. This paper outlines the end-to-end development lifecycle of ZENO, with a focus on its architectural design, system integration, and potential for social adaptability in human-AI interaction.