Projects

A web app that clones the voice of target Nepali speaker and synthesizes the input text to speech in target speaker's voice.

An online browser proctoring application designed to monitor an exam based on audio, video and browser activities.

An embodied agent navigating a 3D Gaussian splat environment using Unity's physics engine, guided by natural language instructions processed through a combined LLM-VLM model. 

An application that extracts relevant info from raw bio data and convert it  into LaTeX formatted resume of desired format using Google Gemini API.