See++ is a web app that lets users analyze their surroundings using a webcam, voice input, and AI — powered by Google's Gemini multimodal model. You can ask questions by clicking a button or speaking, and See++ will respond with both on-screen and spoken answers.

• 📷 Uses your webcam to capture live images
• 🔊 Converts AI responses to speech
• 🗣️ Accepts spoken input through voice recognition
• 🔄 Flip between front and rear cameras
• 🧠 Sends queries and images to Gemini for intelligent answers

git clone https://github.com/ParthParikh04/See.git

python -m venv venv
source venv/bin/activate 

Note: Make sure this virtual environment (venv) is created within the project directory.

pip install -r requirements.txt

1. Visit https://makersuite.google.com/app
2. Sign in with your Google account
3. Click your profile icon (top right) → "API Key"
4. Copy the key

Create a .env file in the root of the project directory with the following contents:

GEMINI_API_KEY=your_api_key_here

🔐 Important: Keep your .env file secret — never share it or commit it to version control.

python app.py

Go to: http://localhost:5000

Want to test See++ on your phone? You can use ngrok to tunnel your localhost and expose it to the internet:

1. Install ngrok

   If you haven't already, install it from https://ngrok.com/download, or use Homebrew:

   brew install ngrok

2. Sign in and authenticate

   Create an account on ngrok and get your auth token from your dashboard. Then run:

   ngrok config add-authtoken your_token_here

3. Start your Flask app

   In one terminal tab, run:

   python app.py

4. Expose your local server with ngrok

   In a new terminal tab, run:

   ngrok http 5000

5. Get the public URL

   ngrok will display a forwarding URL like:

   Forwarding                    https://abc123.ngrok.io -> http://localhost:5000
   

6. Visit on your phone

   Open the https://abc123.ngrok.io link on your phone (make sure your phone and computer are both online).

📸 Your phone will ask for access to the camera and mic — allow these for full functionality.

• Allow access to your webcam and microphone when prompted
• Click a button to:
  • 📄 Extract text from the camera view
  • 🖼️ Describe the current scene
  • 🎤 Use your voice to ask a question
• The app will:
  1. Capture a webcam frame
  2. Send it (along with your question) to the Gemini API
  3. Display and speak the response

• Python 3.7+
• A modern browser (Chrome recommended)
• Internet access
• A Gemini API key from Google

• Parth Parikh
• Andria Wang
• Colby Brown
• James Martin

MIT — use freely, modify creatively, and share responsibly!