Skip to content

MoodSync DJ

MoodSync DJ is an environment-aware, adaptive music generation application.

Code Video Cerebral Valley

Core trick

Gemini 3 reads a webcam frame and maps scene mood to parameters that steer a live Lyria audio stream.

Tags

creative/musicvision

Description

MoodSync DJ is an environment-aware, adaptive music generation application. It solves the problem of static, repetitive background music by leveraging the raw multimodal reasoning power of Gemini 3 to visually analyze your real-world surroundings and directly map that semantic understanding to musical parameters. These parameters govern a continuous, real-time audio stream generated by the Lyria Audio generation model. If Gemini sees a dimly lit bedroom with rain, it generates a lo-fi chill beat; if it sees a vibrant party, it instantly shifts to high-energy dance music. It provides a highly personalized, dynamic soundtrack for your life that reacts to your environment in real-time.
dambor/moodsync-dj★ 00 forksJavaScriptCreated Feb 28, 2026 · last push Feb 28, 2026

README excerpt

# 🎧 MoodSync DJ 

*Built for the [Gemini 3 NYC Hackathon](https://cerebralvalley.ai/e/gemini-3-nyc-hackathon/details) by Cerebral Valley & Google.*

**MoodSync DJ** is an environment-aware, adaptive music generation application. It leverages the raw multimodal reasoning power of **Gemini 3** to visually analyze your real-world surroundings and directly map that semantic understanding to musical parameters, which are then streamed in real-time by the **Lyria Audio Generation Model**.

If Gemini 3 sees a dimly lit bedroom with rain against the window, you get a lo-fi, chill instrumental beat. If it sees a vibrant party with friends, it shifts the Lyria stream to a high-energy dance track. 

![MoodSync DJ Screenshot](public/screenshot.png)

---

## 🌟 Why MoodSync DJ? (Hackathon Focus)

Google asked hackers to push the boundaries of **Gemini 3’s state-of-the-art reasoning** and **rich multimodal understanding**. MoodSync DJ answers that call by:

1. **Multimodal Translation**: It doesn't just describe what it sees—it *interprets* the "vibe" (scene type, energy level, keywords) from your webcam or uploaded images using Gemini 3 Vision capabilities. 
2. **Real-time Parametric Generation**: We use Gemini 3's structured output to dynamically alter Lyria's stream configuration (guidance, brightness, density) and prompt weights on the fly.
3. **Agentic Development**: This entire project was architected, built, and debugged collaboratively using **Antigravity**, Google's new agentic dev

Team