Transform any audio—music, podcasts, stories, documentaries, ads—into stunning synchronized videos with AI-generated visuals.

• Universal Transcription: Transcribes any audio content with word-level timing
• AI Visual Generation: Creates cinematic imagery using Google Gemini or DeAPI
• Smart Storyboarding: Analyzes content structure for emotionally-paced visuals
• Multiple Export Options: Cloud render (fast) or browser-based (private)
• Cross-Platform: Web, Android, and iOS support via Capacitor

Prerequisites: Node.js v18+, FFmpeg (for server export)

# Install dependencies
npm install

# Set up environment
cp .env.example .env.local
# Edit .env.local and add your GEMINI_API_KEY

# Run the app (frontend + backend)
npm run dev:all

See GEMINI.md for detailed architecture, services, and development conventions.

MIT