March to July 2022

Minimal Viable Product for BhumanAI


Generating Multiple Videos with Lip-Sync Support from Single Source Video, in which the timestamps are specified by user and the text to be spoken by the character in the video is mapped to a recorded audio and the output video contains replaced audio and lip-synced character.

As a Front-end Developer, I was responsible for the following tasks:


Raw Prototyping Videos of the Platform

From the CEO of


concluding, the amount of work and in short time shipping something to production helped me to better understand the startup culture of being a small family, working alongside team, collaborating with others and focused on our goals, it's usually burn out days which made the weekends fun for me, spending time on some of my side-projects!

Check Github Repo