GM Text To Voice API - README

This package allows developers to convert text to voice using gm's powerful Text-to-voice (TTS) model. The package enables you to send text input, specify voice options, and receive audio output in a convenient format, such as MP3, for playback or storage.

Features

• Text-to-voice Conversion: Convert text to lifelike voice using gm's TTS model.
• Customizable Voice Selection: Choose from various voices provided by the GM TTS model (e.g., alloy).
• Easy File Output: Save the synthesized voice to an audio file.
• Error Handling: Clear error messages for missing or incorrect input data.

Prerequisites

Before using this package, ensure that you have the following:

Node.js version 14 or higher installed. GM API Key: You need to obtain an API key from gm to use their TTS service. Text Input: The text you wish to convert to voice. Audio Output Path: A path where the resulting audio file (e.g., MP3) will be saved.

Installation:

To install the package, run the following command: npm install gm-text-to-voice

Typical Usage:

const package = require("gm-text-to-voice");
const textFilePath = absolutePathToTextFile;
const apiKey = { apiKey : your-api-key };
const audioPath = absolutePathtoAudioFileCreation/file_name.mp3; 

const textToVoice = new package(textFilePath, apiKey, audioPath);

textToVoice.recognition().then((data) => {
    console.log(data);
}).catch((error) => {
    console.log(error);
});

Example of result:
{
  status: true,
  message: 'Voice synthesis saved to given path : absolutePathtoAudioFileCreation',
}

Exapmle of error:
{
  status: false,
  message: 'Error in synthesis'
}