This project provides real-time audio captioning using OpenAI's Whisper model and AI-powered summarization.

• Real-time audio recording
• Whisper transcription
• Gemini transcription
• AI summary

• Node.js (v18 or higher)
• Yarn (v4.5.3 or higher)
• Python (for Whisper)

1. Install dependencies:

   yarn install

2. Set up Whisper:

   # Install Whisper dependencies (Mac only)
   pip install -U mlx-whisper

1. Start the development server:

   yarn dev

2. In a separate terminal, start the backend server:

   cd server
   yarn dev

3. Open your browser and navigate to http://localhost:5173

• /src - Frontend React application
• /server - Backend server with Whisper integration