Skip to content

A Python app that converts any PDF’s text into speech using offline text-to-speech. It lets you select PDFs via a file picker, reads aloud the extracted text with adjustable speed and volume, and works without an internet connection. Simple, practical, and easy to use for accessible reading.

Notifications You must be signed in to change notification settings

ultimateebeast/text-to-audio

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 

Repository files navigation

🔊 Text-to-Audio PDF Reader (Python)

A modern, Python-based tool that reads aloud the content of any PDF file using text-to-speech (TTS). Built with PyPDF2, tkinter, and pyttsx3, this application extracts all readable text from a PDF (such as books or documents) and speaks it using your system's voice engine. It now features a visual file picker popup for selecting files easily.


📚 Features

  • 📂 Choose PDF file via file picker (no path typing!)
  • 📄 Extracts text from standard, searchable PDF files
  • 🔊 Reads the extracted text aloud using TTS
  • 🧠 Works completely offline — no internet required
  • 🎧 System voice support with adjustable rate/volume
  • 📝 Optional support for summarizing the spoken content (coming soon)

🛠 Requirements

Install the required Python libraries:

pip install PyPDF2 pyttsx3 pyaudio colorama 🧠 tkinter comes pre-installed with Python, no need to install it separately.

▶️ How to Use Clone the repository:

git clone https://github.com/ultimateebeast/text-to-audio cd text-to-audio Run the script:

python main.py Choose a PDF file using the popup file selector.

The program will extract the text and start reading it aloud using your system's default voice.

📌 Notes Works best with searchable PDFs (not scanned/image-based ones).

Pages without readable text will be skipped automatically.

All processing is done locally — your data never leaves your device.

🧑‍💻 Author Pratyush Jain 🔗 GitHub: @ultimateebeast

📄 License This project is licensed under the MIT License.

About

A Python app that converts any PDF’s text into speech using offline text-to-speech. It lets you select PDFs via a file picker, reads aloud the extracted text with adjustable speed and volume, and works without an internet connection. Simple, practical, and easy to use for accessible reading.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages