Text-to-Speech-Conversion

This repository contains a python script which converts the text from a PDF file into an mp3 audio file. This code uses file handling in python and relies on some external libraries.

Some libraries used in this python code:

tempfile : creates temporary file to contain .ppm image files for fast input-output
pdf2image : converts pdfs to images
PIL.Image : supports opening, manipulating and saving images
pytesseract : converts written content of an image to text
gtts : Google Translate's text-to-speech API

References:

Do go through this blog to get more insights about the project:
https://myblindbird.com/python-project-source-code/