Gita: AI-Powered Video-to-Music Generation Platform

It captures the emotional transformation from "bland to beautiful" while highlighting the speed and AI technology, making it both personal and impressive.

Comment

Inspiration

You finished your video. It looks amazing. You just need to find the right music. But that’s the hard part. You spend hours searching for a good song that won’t get your video taken down by a copyright claim. It’s a huge headache, and it kills your creative momentum. We think that’s backward. Finding music should be inspiring, not frustrating. That’s why we’re making Gita. What if you could create your own unique, copyright-safe music that matches the vibe of your video, just by uploading it?

What it does

Finding the right music for your video is a huge pain. It takes forever, and the good stuff either costs a lot or comes with scary copyright rules. We built Gita to fix that. It’s simple. You give Gita your finished video, and it creates a brand new soundtrack that matches the energy and emotion of your footage. The music is 100% yours to use, and of course, copyright-free. No more searching. No more fees. Just your video, with the perfect background music.

Tech stack

  • React: Powers the user-friendly website where people upload their videos and interact with Gita.
  • Python: Serves as the core programming language for our backend, connecting all the different services and agents together.
  • FastAPI: Creates the high-speed API that allows our React frontend to communicate with the Python backend and AI agents.
  • Google ADK: Provides the framework for building and orchestrating our team of specialized AI agents that analyze the video and create the music.
  • Gemini (Lyria AI): Acts as the creative AI "brain" that actually generates unique, instrumental background music based on the text prompts our agents create.
  • Groq: A specialized AI hardware platform we use to generate detailed prompt for Lyria AI to generate music.

AI agents

  • Video Processor: The initial agent that analyzes the uploaded video to extract key visual and audio information for the AI to understand.
  • Prompt Generator: An AI agent that takes the video analysis and creatively writes the detailed text instruction needed for the music AI.
  • Prompt Checker: A validation step or agent that ensures the generated text prompt is clear, safe, and well-structured before sending it to the music AI.
  • Music Generator: The core creative AI, Lyria, that reads the final prompt and composes a unique, instrumental piece of background music.
  • Orchestrator: The master agent that manages the entire workflow, telling each component when to start and passing the data between them from start to finish.

Next Steps

  • More Customization: We will give users more creative control by letting them select genres, choose specific instruments, or adjust the tempo of their generated music.
  • More Fine-Tuning: We will train our AI agents on more specific examples to make them better at understanding the nuances of a video and creating more accurate, emotionally resonant music.

Built With

Share this project:

Updates