tomdwipo / Gemini-Vision-Pro

Google Gemini Vision Web application with Speech and Text

🚀 Description: 🚀 This is the amazing Google Gemini Vision Pro 📸, a powerful tool that scans images, generates descriptions using Gemini AI Pro Vision API, and provides speech feedback 🗣️. It also captures images using the webcam 🖥️.

🌟 Introduction 🌟

Google Gemini Vision Pro is a versatile application that combines image processing 🖼️, speech recognition 🎤, and text-to-speech capabilities 📢. With this application, you can capture images using your webcam 📷, convert spoken words to text 📝, generate image descriptions 📚, and even have the descriptions spoken back to you 📣.

Installation Guide

Step 1: Clone the repository

git clone https://github.com/haseeb-heaven/Gemini-Vision-Pro
cd Gemini-Vision-Pro

Step 2: Install the dependencies

pip install -r requirements.txt

Step 3: Run the application

streamlit run script.py

Step 4: Obtain the Google Palm API key and Setup the application

1. Obtain the Google Palm API key.
2. Visit the following URL: Google AI Studio
3. Click on the Create API Key button.
4. The generated key is your API key. Please make sure to copy it and paste it in the application settings.
5. The API key is crucial for the functioning, Please ensure to keep it safe and do not share it with anyone.

Gemini AI settings:

AI Sections

The core AI sections of this project include:

• 📷 Webcam detection using WebRTC, OpenCV, and PIL
• 🗣️ Speech-to-text conversion using Google Cloud Speech-to-Text API
• 🎙️ Text-to-speech conversion using Google Cloud Text-to-Speech API
• 📸 Image processing using Gemini AI Pro Vision API

Features

• 📷 Webcam detection with real-time image capture
• 🗣️ Speech-to-text conversion for spoken words
• 🎙️ Text-to-speech for generating spoken descriptions
• 📸 Image processing using AI to provide detailed descriptions
• 📝 Logging using Python's logging module
• ⚙️ Error handling with Python's exception handling

WebUI - Application Showcase

YouTube demo:

Webcam with live feed:

Gemini Ai Vision demo with object as Cap:

Gemini Ai Vision demo with Hand:

Gemini Ai Vision demo with Gesture:

Packages Used

This project relies on various Python packages, including:

• Streamlit - A web app framework used to build the application
• Streamlit Webrtc - Used for capturing images from the webcam
• OpenCV - Utilized for webcam image capture
• PIL (Pillow) - Used for image processing and conversion
• gTTS (Google Text-to-Speech) - Converts text to speech
• SpeechRecognition - Converts speech to text
• google.cloud.speech - Part of Google Cloud services for speech-to-text conversion

📚 Links and References

Follow these links for Google Gemini Vision Pro related content:

• Google AI Studio
• Google Gemini Vision Pro
• Google Gemini Deepmind

Versioning

• Version: 1.0 : Initial Release

Contributing

We welcome contributions! Please follow our Contribution Guidelines to get started.

License

This project is licensed under the MIT License - see the LICENSE file for details.

Author

• HeavenHM
• Date: 17-12-2023