AWS Textract and Polly

Project name --> Textify

This project demonstrates the use of Python Tkinter for a graphical user interface (GUI) to upload images. The text extracted from these images using AWS Textract is then converted to speech using AWS Polly.

Features

• GUI for Image Upload: A simple and user-friendly interface to upload images.
• Live preview of the uploaded image
• Text Extraction: Uses AWS Textract to extract text from uploaded images.
• Voice Generation: Uses AWS Polly to convert the extracted text to speech.
• Downloadable Audio: The generated audio can be saved locally.

Flowchart and working

Here is the simple working flowchart of the project

Thank you :)

Dependencies

• Boto3
• Tkinter
• Pillow

Installation

1. Clone the repository

 https://github.com/Dacrron/Textify-AWS.git

2. Install all required packages
3. Configure your AWS profile with the appropriate user with AWS CLI
4. Edit your user name inside the code, upload image and there you have it.

Screenshots

Acknowledgements

• AWS TEXTRACT
• Boto3
• AWS Polly