Skip to content

ASHWIN492/VAANI---Empowering-Inclusive-Communication-through-AI

Repository files navigation

VAANI - Empowering Inclusive Communication through AI

VAANI is a software designed to empower individuals with visual impairments by providing inclusive access to various forms of content through AI-driven technologies.

Features

Text-to-Speech

Convert text into speech in multiple languages. Users can either directly input text or upload a PDF file containing the text they want to convert.

Image Captioning

Generate descriptive captions for uploaded images. VAANI analyzes the content of the image and provides a verbal description of what is happening in the scene.

Record Voice Note

Start recording voice notes, which are saved for future reference. This functionality allows users to create audio recordings for personal memos or messages.

Read Braille

Convert Braille text into speech. Users can input Braille text, and VAANI will convert it into spoken language for auditory consumption.

Getting Started

Installation

  1. Clone the repository:
    git clone https://github.com/your_username/VAANI.git
  2. Navigate to the project directory:
    cd VAANI
  3. Install the required dependencies:
    pip install -r requirements.txt
  4. To run the VAANI application, execute the following command in your terminal:
    streamlit run app.py

Contributors

Name GitHub ID
Atharv Amit Gangrade athhhh
Sagar Chaudhary SAGARCHRY0777

About

No description, website, or topics provided.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages