A Next.js application combining Gemini 2.5 Flash Image and ElevenLabs Audio for innovative multimodal experiences.
-
Install dependencies:
npm install
-
Configure environment variables: Copy
.env.localand add your API keys:GEMINI_API_KEY=your_gemini_api_key_here ELEVENLABS_API_KEY=your_elevenlabs_api_key_here ELEVENLABS_VOICE_ID=your_preferred_voice_id_here
-
Run the development server:
npm run dev
- Framework: Next.js 15 + TypeScript
- Styling: Tailwind CSS
- AI Models: Gemini 2.5 Flash Image (NanoBanana)
- Audio: ElevenLabs Text-to-Speech
- Development: ESLint + Fast Refresh
src/
├── app/ # Next.js app router
├── components/ # Reusable UI components
├── lib/ # API clients and utilities
│ ├── gemini.ts # Gemini API integration
│ ├── elevenlabs.ts # ElevenLabs API integration
│ └── index.ts # Utilities and exports
└── types/ # TypeScript definitions
- Image analysis and understanding
- Text extraction from images
- Creative descriptions for audio narration
- Multi-modal content generation
- High-quality text-to-speech
- Multiple voice options
- Mood-based audio generation
- Real-time audio synthesis
npm run dev # Start development server
npm run build # Build for production
npm run start # Start production server
npm run lint # Run ESLintSee HACKATHON_CONTEXT.md for detailed planning, innovation opportunities, and competitive advantages.
Ready to build something amazing! 🚀