DreamStudio: AI Cinematic Story Director
Speak naturally, point your camera, and watch scenes materialize as images, video, and music in real-time
DreamStudio is an AI-powered cinematic story director that transforms voice input and camera feeds into complete multimedia scenes. Using Google's Gemini Live API for real-time scene understanding, it orchestrates three generation models simultaneously: Imagen 4 for still images, Veo 3.1 for video clips, and Lyria 2 for background music.
The system is fully cross-platform with a React web app, Flutter mobile app, and Python Flask backend. Users describe a scene naturally ("a foggy Victorian street at dusk with gas lamps") and DreamStudio generates matching visuals and soundtrack in real-time, creating an immersive cinematic experience.
Key Highlights
3
Platforms (Web, Mobile, API)
4
Google AI Models
Real-time
Generation Speed
270K+
Lines of Code
Architecture Details
- Gemini Live API: Real-time voice and camera input processing for scene understanding and story direction.
- Multi-Model Orchestration: Coordinates Imagen 4 (images), Veo 3.1 (video), and Lyria 2 (music) generation in parallel.
- Cross-Platform: React web app for desktop, Flutter/Dart mobile app for iOS/Android, shared Python Flask backend.
- Real-Time Pipeline: Voice input is processed, scenes are understood, and media is generated with minimal latency for an interactive experience.
Tech Stack
Gemini Live APIImagen 4Veo 3.1Lyria 2
FlutterReactPythonFlask