watson Text to speech using socket

Question

How do i implement watson text to speech while running a chatbot on a local host using nodejs?

My chatbot is already running on a localhost..I want to embed watson text to speech service. I have read that it could be done by websocket interfacing. I don t have any idea on that

Sayuri Mizuguchi Sayuri Mizuguchi · Accepted Answer · 2017-10-04T14:56:51

Assuming that you have the Conversation Simple example built by IBM Developers using Node.js and Conversation Service, you can simply have your app submit an HTTP REST request by following this tutorial using Websocket or you can leverage a language-specific SDK, I'll paste in the links below.

So, a few months ago the @kane built one example that integrates the conversation simple example with text to speech, you can easily found them in this link.

You can check this commit for saw the changes and follow the logic to implement Text to Speech in your application. You'll see this code above calling the Text to Speech service with the Services credentials in the .env file, like the comments in the code:

const TextToSpeechV1 = require('watson-developer-cloud/text-to-speech/v1');

const textToSpeech = new TextToSpeechV1({
  // If unspecified here, the TEXT_TO_SPEECH_USERNAME and
  // TEXT_TO_SPEECH_PASSWORD env properties will be checked
  // After that, the SDK will fall back to the bluemix-provided VCAP_SERVICES environment property
  // username: '<username>',
  // password: '<password>',
});

app.get('/api/synthesize', (req, res, next) => {
  const transcript = textToSpeech.synthesize(req.query);
  transcript.on('response', (response) => {
    if (req.query.download) {
      if (req.query.accept && req.query.accept === 'audio/wav') {
        response.headers['content-disposition'] = 'attachment; filename=transcript.wav';
      } else {
        response.headers['content-disposition'] = 'attachment; filename=transcript.ogg';
      }
    }
  });
  transcript.on('error', next);
  transcript.pipe(res);
});

// Return the list of voices
app.get('/api/voices', (req, res, next) => {
  textToSpeech.voices(null, (error, voices) => {
    if (error) {
      return next(error);
    }
    res.json(voices);
  });
});

Obs.: I suggest to you see the Commit and follow the same logic to make your changes in your app.

Node SDK for Watson Services.
API Reference for using Text to Speech with Node.js

watson Text to speech using socket

1 Answers