textToSpeech.ts

import { config } from "./config";
import fs from "fs";
import * as fileHelpers from "./helper";
import request from "request";

convertTextToSpeech("In mindfulness practice, we are learning how to return to the moment");

function convertTextToSpeech(inputText: string) {
  const authRequestOptions: request.CoreOptions = {
    headers: {
      "Ocp-Apim-Subscription-Key": config.texttospeechkey
    }
  };

  let base_url = 'https://westus.tts.speech.microsoft.com/'
  let path = 'cognitiveservices/v1';
  let full_url = base_url + path;

  request.post(
    config.texttospeechendpoint,
    authRequestOptions,
    (err, response, body) => {
      if (err) {
        console.log('err', err);
      }
      const accessToken = response.body;
      // console.log('response body', accessToken);

      const payLoad = `<speak version='1.0' xml:lang='en-US'>
          <voice xml:lang='en-US' xml:gender='Female' name='Microsoft Server Speech Text to Speech Voice (en-US, ZiraRUS)'>
          ${inputText}
          </voice>
          </speak>`;

      const requestOptions: request.CoreOptions = {
        headers: {
          "X-Microsoft-OutputFormat": "audio-24khz-96kbitrate-mono-mp3",
          "Content-Type": "application/ssml+xml",
          "Content-Length": payLoad.length,
          "Authorization": "Bearer " + accessToken,
          "User-Agent": "NodeJS"
        },
        body: payLoad
      };
      request.post(
        full_url,
        requestOptions,
        (err, response, body) => {
          if (err) {
            console.log('err or!', err)
          }
          var convertedAudio = Buffer.from(response.body);
          fs.writeFileSync(__dirname + "/output.mp3", response.body,
            { encoding: 'binary' });
        }
      )

    }
  );
}