GM Recognition API - README

This package is a simple Node.js library designed for recognizing speech from audio files using gmt model for transcription. It allows you to upload an audio file, provide an gmt API key, and get the transcription results from the gmt model.

Features

Audio Transcription: Automatically transcribes audio files into text using the gmt-model. Error Handling: Provides informative error messages for missing or incorrect input data. Simple API: Easy integration with gmt API using your personal API key.

Prerequisites

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

Node.js version 14 or higher installed. An gmt API key. Audio files for transcription (e.g., mp3, mp4, mpeg, mpga, m4a, wav, and webm).

Installation:

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

Typical Usage:

const package = require("gm-voice-to-text");
const audioFile = absolutePathToAudioFile;
const apiKey = { apiKey : your-api-key };
const type = "OpenAI" or "Google";

const const speechTotext = new package(audioFile,apiKey,type);

const result = speechTotext.recognition().then((data) => {
    console.log(data);
}).catch((error) => {
    console.log(error);
});

Example of result:
{
  status: true,
  message: 'Recognition successful',
  data: { text: "Hello World" }
}

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