Solshine's picture
Update README.md
a1f5b6e verified

A newer version of the Streamlit SDK is available: 1.40.1

Upgrade
metadata
title: gTTS-PDF-text-to-speech
emoji: πŸ“Š
colorFrom: green
colorTo: gray
sdk: streamlit
sdk_version: 1.32.0
app_file: app.py
pinned: false
license: apache-2.0
short_description: Accessibility PDF & pasted text to speech converter w/ gTTs

GitHub: https://github.com/SolshineCode/gTTS-PDF-text-to-speech/blob/main/README.md

Hear Ye, Hear Ye! The gTTS-PDF-Text-to-Speech Accessibility Odyssey Awaits! πŸ§™πŸ½β€β™‚οΈ

Welcome, travelers of the digital realm, to the grand expedition of gTTS-PDF-text-to-speech! We're here to vanquish the tyranny of silent PDFs and transform those pesky documents into a delightful audio adventure for your ears.

This open-source project, available to use now on Hugging Face Spaces (hit the "App" tab above), boasts two mighty features:

  • PDF Slayer: ️ Conquer those PDFs! Upload your document and choose the number of pages you wish to hear spoken aloud. Lean back, relax, and let the "soothing" tones of the Google Text-to-Speech engine (gTTS) guide you through the text.

  • Text Transmuter: πŸͺ„ Got some text you want spoken? Don't let it gather dust! Paste it in the chat or type it directly, and witness the magic! Our text-to-speech wizard will weave its sonic spell, bringing your words to life.

But wait, there's more! This is just the beginning of our quest. We envision a future where this project embraces the power of neural networks to create even more natural-sounding voices.

This is about more than convenience; it's about accessibility. We strive for a world where neurodivergent folks and those with accessibility needs have a wealth of tools at their disposal, empowering them to learn, work, and explore information seamlessly. Imagine using this app in educational settings, professional environments, or even listening to documents while driving! The possibilities are endless!

Ready to join the adventure? Here's a glimpse of the wondrous Streamlit interface that awaits:

  • A Warm Welcome: Our mascot (a tiny llama librarian friend!) greets you at the start of your journey.
  • The Pageinator: This nifty slider allows you to select the number of PDF pages you want to hear.
  • The Treasure Chest: Here, you upload your precious PDF document.
  • The Magic Text Box: Paste or type text here to unleash the power of text-to-speech!
  • The Audio Gallery: This is where the magic happens! Listen to the spoken renditions of your PDFs and text.

Calling All Code Crusaders! βš”οΈ

This project is open-source, meaning anyone can contribute! If you're a coding wizard, feel free to explore the code on GitHub, tinker with it, and suggest improvements. Together, we can build a more accessible and inclusive digital world!

A Glimpse into the Future:

Keep your eyes peeled for upcoming updates! We're working on integrating neural networks for life-like text-to-speech, and expanding functionalities to cater to a wider range of needs.

Let's embark on this glorious quest together! May your PDFs be vanquished, and your text transformed into delightful audio experiences!