Skip to content
This repository has been archived by the owner on Jul 22, 2024. It is now read-only.
/ pitchula Public archive

Convert any text in a image file into audio with a single command line.

License

Notifications You must be signed in to change notification settings

lucasmence/pitchula

Repository files navigation

Code Quality

 Pitchula Text Photoreader

Current version: 1.0.2

Convert any image-text into audio with a single command line, e. g.:

python pitchula.py input.jpg output.mp3

Languages

The project has avaiable these four languages right now!

How to install

  • Clone the project directory using git clone command:

git clone https://github.com/lucasmence/pitchula-photoreader/

  • Install the OpenCV library for python using the command below:

pip install opencv-python

  • Install the Pillow library using the command below:

pip install Pillow

  • Install the python-setuptools using the command below:

sudo apt install python-setuptools

  • Install the Tesseract-OCR libraries to continue, just copy the commands below:

sudo apt install tesseract-ocr

sudo apt install libtesseract-dev

  • Install the Tesseract for python library using the command below:

pip install pytesseract

  • Install the spellcheck libraries, enchant and pyenchant, just use the commands below:

sudo apt install enchant

pip install pyenchant

  • Install the text-to-speech API library the gTTS by using the command below:

pip install gTTS

Okay, now you're ready to use this tool!

Extensions

Input image types suported: JPG and PNG

Output audio type suported: MP3

Credits

OpenCV for Python library

Pillow library

python-setuptools

Tesseract-OCR library

pytesseract library

pyenchant library

Google Text-to-Speech

Icons

Project logo icon and country flags made by Freepik from www.flaticon.com is licensed by CC 3.0 BY

version-log

01/28/2019: Released the version 1.0.2

> Object instance otimization for a better performance;

> Fixed languagePath definition bug;

> Updated the languages JSON files w/ new repository environment;

01/27/2019: Released the version 1.0.1

> Removed unused lines;

> Updated all the project files to use OOP;

> Replaced the run.py file to pitchula.py to test the project;

> Use the Reader class on reader.py file to use the project functions inside of your own project;

12/23/2018: Released the version 1.0.0

Last update: July, 22 of 2024.

About

Convert any text in a image file into audio with a single command line.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages