SeeSpeakTranslate_GUI

Description

This project provides a content description application that can analyze frames from real-time video streams, supports multiple languages, and includes text-to-speech (TTS) capabilities. Utilizing powerful AI models from Google, the application analyzes images and delivers descriptions in various languages, which can also be audibly presented. It features a user-friendly interface with customizable style options.

Features

• Real-Time Video Streaming: View and manage video streams from different camera sources.
• Frame Description: AI-powered content description that analyzes and describes video frames.
• Multi-Language Support: Content descriptions in English, Turkish, German, and Arabic.
• Text-to-Speech Conversion: Listen to descriptions in the selected language.
• User-Friendly Interface: Intuitive and easy-to-use interface.
• Customizable Style: Personalize the application's appearance with style settings.

Files and Modules

1. content_description.py:
   • Contains the content description class and functions.
   • Provides user input handling, frame description, and text-to-speech functionality.
2. main.py:
   • The main entry point of the application.
   • Sets up the user interface using Tkinter and applies style settings.
   • Initializes the video stream handler and content describer objects.
3. video_stream.py:
   • Contains the class that manages video streaming.
   • Processes video streams from the camera and displays them on a Tkinter Canvas.
   • Provides functions to start, stop, and update the video stream.

Usage

1. Install Required Libraries:

   pip install -r requirements.txt

2. Set Up Environment Variables:

   Add your Google API key to the .env file.

3. Run the Application:

   python main.py

4. Select Camera and Language:

   In the application interface, select a camera from the available options and choose the desired description language.

5. Start Video Stream and Get Description:

   • Press the "Select Camera" button to start the video stream.
   • Press the "Describe the frame" button to get the description of the video frame.
   • Press the "Text-to-Speech" button to hear the description audibly.

Example

To see an example of the application in action, refer to the following steps:

1. Select Camera: Choose the desired camera source from the dropdown menu.
2. Select Language: Choose the language for the description from the language menu.
3. Start Video Stream: Click "Select Camera" to start the video stream.
4. Describe Frame: Click "Describe the frame" to get a textual description of the current video frame.
5. Text-to-Speech: Click "Text-to-Speech" to hear the description spoken aloud.