Voice Activated AI Virtual Assistant

Access the GitHub repository for the project here

A brief presentation summarising the project and results can be found here and J.E.S.S.I.E can be seen in action here.

Introducing J.E.S.S.I.E. (Just Enhanced Speech Synthesis and Intelligent Execution), the advanced voice-assistant developed as part of the DSCBVP MANIFESTE hackathon. Built in Python 3.7+, J.E.S.S.I.E. redefines the user experience by understanding human speech, engaging in chit chat, and executing commands for AI Automation. With a wide range of capabilities, J.E.S.S.I.E. transforms device interactions into seamless and efficient experiences.

J.E.S.S.I.E. goes beyond a typical voice-assistant with its exceptional capabilities. From greetings and chit chat to playing games and sharing hilarious jokes, J.E.S.S.I.E. ensures an entertaining experience. It opens websites like Google, Gmail, and YouTube, performs operations with Google Maps, and can even capture selfies using the webcam. Sending emails, texting, opening system applications, creating lists, playing music, and podcasts are just a few of the practical tasks J.E.S.S.I.E. effortlessly handles. Additionally, it provides real-time information such as the current date and time, weather updates, Mars images from NASA, and COVID-19 updates.

With asynchronous command execution and support for voice or text inputs, J.E.S.S.I.E. offers a user-friendly interface. Users can interact naturally through voice commands and receive responses in either audio or text format. J.E.S.S.I.E. is the ultimate voice-assistant, simplifying AI Automation and enhancing efficiency in everyday tasks.