PowerPoint Text-to-Speech Extension with React JS

PowerPoint Text-to-Speech Extension

This is a README.md file providing an overview and essential information about the PowerPoint Text-to-Speech Extension developed using the Yeoman generator and React JS. The extension is a part of a text-to-speech based system, facilitating SSML conversion, ANSI to Unicode conversion, and utilizing TTS API for generating audio from selected text within PowerPoint presentations.

Introduction

The PowerPoint Text-to-Speech Extension is a custom task pane for Microsoft PowerPoint, designed to provide a seamless text-to-speech experience for users. The extension allows users to convert text to SSML format, perform ANSI to Unicode conversion, and subsequently generate audio using the deployed TTS models through API requests. The audio is asynchronously fetched from the server and played synchronously to facilitate a smooth user experience.

Features

• Text to SSML conversion
• ANSI to Unicode conversion
• Seamless integration with PowerPoint's custom task pane
• Easy-to-use play buttons for audio generation
• Asynchronous API requests for audio generation
• Synchronous audio playback

Installation

To install the PowerPoint Text-to-Speech Extension, follow these steps:

• Clone the repository from GitHub:

git clone https://github.com/eliashossain001/Yo_PowerpointAddInTTS.git

• Navigate to the extension's directory:

cd your repository

• Install the necessary dependencies:

npm install

Install Yeoman and the Yeoman generator for Office Add-ins

• Make sure you have Node.js and npm (Node Package Manager) installed. Then, install Yeoman and the Yeoman generator for Office Add-ins:

npm install -g yo generator-office

• Generate the PowerPoint extension project, Create a new directory for your project and navigate into it:

mkdir powerpoint-extension
cd powerpoint-extension

• Now, generate the PowerPoint extension project using Yeoman:

yo office

Usage

Once the extension is installed, you can run it in development mode using the following command: npm start This will launch the extension in your default web browser, and you can now access it via PowerPoint's custom task pane.

Process of Audio Chunking

How It Works

1. The user opens PowerPoint and enables the custom task pane, which contains the text-to-speech extension.
2. The extension provides options for text selection, SSML conversion, and ANSI to Unicode conversion.
3. Upon clicking the play button, the selected text is sent via asynchronous API requests to the server where the TTS models are deployed.
4. The server processes the text, chunks it into suitable portions, and generates audio for each chunk.
5. The audio chunks are then fetched from the server asynchronously.
6. Once the audio is received, it is played synchronously to the user, providing an instant text-to-speech experience within PowerPoint.

Dependencies

The PowerPoint Text-to-Speech Extension relies on the following key dependencies:

1. React: A JavaScript library for building user interfaces.
2. Yeoman: A scaffolding tool to generate project templates.
3. TTS API: An API hosting the text-to-speech models used for audio generation.

For a complete list of dependencies, please refer to the package.json file in the project repository.