The Music Media Agent is an autonomous content director that uses Gemini Vision to watch and analyze visual media. From there it generates a matching 30 second AI soundtrack and automatically syncs it into a finished video file. It automates a complex post production workflow that would normally require multiple tools and a lot of manual work all within a single agent.
Joshua Ndala is a UBC CS graduate and software developer with a passion for AI/ML and generative media. With global academic experiences and hands-on projects, he has sharpened his problem-solving skills and adaptability. He works primarily with Python, JavaScript, and SQL, building tools that make tech useful and data impactful. His work focuses on making high-level content creation more accessible by leveraging multimodal AI to streamline creative workflows, especially in video and music production. Joshua is looking to contribute to a team in software development or machine learning engineering.
Try out the Music Media Agent below and see how it transforms your video into a finished piece with a fully synced AI generated soundtrack. Just upload your clip and let the agent handle the rest.
