EventMind is a web platform for intelligent image and audio processing that leverages OCR and AI-driven analysis to transform visual and audio data into actionable insights.
- Dual Media Processing: Process both images (with OCR) and audio files (with speech-to-text)
- AI-Powered Analysis: Extract key insights from images and audio with advanced AI analysis
- Workspace Organization: Manage media files in customizable workspaces
- Shared Insights: Connect insights across different media files
- Bulk Processing: Process multiple files at once with batch operations
- Action Item Generation: Automatically generate tasks from insights
- ClickUp Integration: Export action items directly to ClickUp
- Export Options: Export insights as PDF, Word documents, or plain text
- Visual Knowledge Base: Build a repository of connected visual insights
- Frontend: React, TypeScript, Tailwind CSS with shadcn/ui components
- Backend: Node.js, Express
- Database: PostgreSQL with Drizzle ORM
- AI Services: OpenAI GPT-4V for image analysis, Whisper API for audio transcription
- OCR Engine: Tesseract.js for text extraction from images
- Clone the repository
- Install dependencies with
npm install - Set up required environment variables:
DATABASE_URL: PostgreSQL connection stringOPENAI_API_KEY: OpenAI API key for AI analysisCLICKUP_API_KEY: ClickUp API key for task integration (optional)
- Run database migrations with
npm run db:push - Start the development server with
npm run dev
The following environment variables are required:
DATABASE_URL: PostgreSQL connection stringOPENAI_API_KEY: OpenAI API key for GPT-4V and Whisper APICLICKUP_API_KEY: ClickUp API key (optional, for task integration)
- Register and login to the platform
- Upload images and audio files to your workspace
- View processed insights and extracted text
- Generate action items from insights
- Export insights to various formats
- Integrate with ClickUp for task management