Handle user input with ASR

Prerequisites

npm install -g nexmo-cli

nexmo app:create "User Input ASR Example" http://demo.ngrok.io/webhooks/answer http://demo.ngrok.io/webhooks/events --keyfile private.key

compile 'com.vonage:client:6.2.0'
compile 'com.sparkjava:spark-core:2.7.2'

Write the code

Add the following to the main method of the AsrInput class:

/*
 * Route to answer incoming calls.
 */
Route answerCallRoute = (req, res) -> {
    TalkAction intro = TalkAction
            .builder("Please say something")
            .build();

    SpeechSettings speechSettings = new SpeechSettings();
    speechSettings.setLanguage(SpeechSettings.Language.ENGLISH_UNITED_STATES);

    InputAction input = InputAction.builder()
            .type(Collections.singletonList("speech"))
            .eventUrl(String.format("%s://%s/webhooks/asr", req.scheme(), req.host()))
            .speech(speechSettings)
            .build();


    res.type("application/json");

    return new Ncco(intro, input).toJson();
};

/*
 * Route which returns NCCO saying which word was recognized.
 */
Route speechInputRoute = (req, res) -> {
    InputEvent event = InputEvent.fromJson(req.body());

    TalkAction response = TalkAction.builder(String.format("You said %s, Goodbye.",
            event.getSpeech().getResults().iterator().next().getText()
    )).build();
    res.type("application/json");

    return new Ncco(response).toJson();
};

Spark.port(3000);
Spark.get("/webhooks/answer", answerCallRoute);
Spark.post("/webhooks/asr", speechInputRoute);

View full source

Run your code

We can use the application plugin for Gradle to simplify the running of our application. Update your build.gradle with the following:

  apply plugin: 'application'
  mainClassName = project.hasProperty('main') ? project.getProperty('main') : ''

Run the following gradle command to execute your application, replacing com.vonage.quickstart.voice with the package containing AsrInput:

gradle run -Pmain=com.vonage.quickstart.voice.AsrInput

Prerequisites

npm install -g nexmo-cli

nexmo app:create "User Input ASR Example" http://demo.ngrok.io/webhooks/answer http://demo.ngrok.io/webhooks/events --keyfile private.key

Install-Package Vonage

{
    public class AsrController : Controller
    {
        [HttpGet("[controller]/webhooks/answer")]

Write the code

Add the following to AsrController.cs:

            var request = WebhookParser.ParseQuery<Answer>(Request.Query);
            var eventUrl = $"{Request.Scheme}://{host}/webhooks/asr";
            var speechSettings = new SpeechSettings { Language = "en-US", EndOnSilence = 1, Uuid = new[] { request.Uuid } };
            var inputAction = new MultiInputAction { Speech = speechSettings, EventUrl = new[] { eventUrl } };

            var talkAction = new TalkAction { Text = "Please speak now" };

            var ncco = new Ncco(talkAction, inputAction);
            return Ok(ncco.ToString());
        }

        [HttpPost("/webhooks/asr")]
        public async Task<IActionResult> OnInput()
        {            
            var input = await WebhookParser.ParseWebhookAsync<MultiInput>(Request.Body, Request.ContentType);
            var talkAction = new TalkAction();
            talkAction.Text = input.Speech.SpeechResults[0].Text;
            var ncco = new Ncco(talkAction);
            return Ok(ncco.ToString());
        }
    }
}

View full source

Prerequisites

npm install -g nexmo-cli

nexmo app:create "User Input ASR Example" http://demo.ngrok.io/webhooks/answer http://demo.ngrok.io/webhooks/events --keyfile private.key

composer require slim/slim:^3.8

Write the code

Add the following to index.php:

use Vonage\Voice\NCCO\Action\Talk;
use Vonage\Voice\NCCO\Action\Input;
use \Psr\Http\Message\ResponseInterface as Response;
use \Psr\Http\Message\ServerRequestInterface as Request;

require 'vendor/autoload.php';

$app = new \Slim\App;

$app->get('/webhooks/answer', function (Request $request, Response $response) {
    $uri = $request->getUri();
    $url = $uri->getScheme().'://'.$uri->getHost().':'.$uri->getPort().'/webhooks/asr';

    $inputAction = new Input();
    $inputAction
        ->setSpeechEndOnSilence(true)
        ->setSpeechLanguage('en-US')
        ->setEventWebhook(new Webhook($url))
    ;
    $ncco = new NCCO();
    $ncco
        ->addAction(new Talk('Please say something'))
        ->addAction($inputAction)
    ;

    return $response->withJson($ncco->toArray());
});

$app->map(['GET', 'POST'], '/webhooks/asr', function (Request $request, Response $response) {
    /** @var InputWebhook $input */
    $input = Factory::createFromRequest($request);

    $ncco = new NCCO();
    $ncco->addAction(new Talk('You said ' . $input->getSpeech()['results'][0]['text']));

    return $response->withJson($ncco->toArray());
});

$app->run();

View full source

Run your code

Save this file to your machine and run it:

php -t . -S localhost:3000

Prerequisites

npm install -g nexmo-cli

nexmo app:create "User Input ASR Example" http://demo.ngrok.io/webhooks/answer http://demo.ngrok.io/webhooks/events --keyfile private.key

pip install Flask request jsonify

#!/usr/bin/env python3
from flask import Flask, request, jsonify

app = Flask(__name__)

Write the code

Add the following to handle-user-input-with-asr.py:

@app.route("/webhooks/answer", methods=["POST", "GET"])
def answer_call():
    ncco = [
        {"action": "talk", "text": "Please, tell me something",},
        {
            "action": "input",
            "type": ["speech"],
            "eventUrl": [
                "{host}{endpoint}".format(
                    host=request.host_url, endpoint="webhooks/asr"
                )
            ],
            "speech": {
                "endOnSilence": 1,
                "language": "en-US",
                "uuid": [request.args.get("uuid")],
            },
        },
    ]
    return jsonify(ncco)


@app.route("/webhooks/asr", methods=["POST", "GET"])
def answer_asr():
    body = request.get_json()
    if body is not None and "speech" in body:
        speech = body["speech"]["results"][0]["text"]
        ncco = [
            {"action": "talk", "text": "Hello ,you said {speech}".format(speech=speech)}
        ]
    else:
        ncco = [{"action": "talk", "text": "Sorry, i don't undertand. Bye"}]

    return jsonify(ncco)


if __name__ == "__main__":
    app.run(port=3000)

View full source

Run your code

Save this file to your machine and run it:

python handle-user-input-with-asr.py

Prerequisites

npm install -g nexmo-cli

nexmo app:create "User Input ASR Example" http://demo.ngrok.io/webhooks/answer http://demo.ngrok.io/webhooks/events --keyfile private.key

gem install sinatra sinatra-contrib rack-contrib

require 'sinatra'
require 'sinatra/multi_route'
require 'rack/contrib'

use Rack::JSONBodyParser

Write the code

Add the following to answer-inbound-call-with-asr.rb:

before do
  content_type :json
end

route :get, :post, '/webhooks/answer' do
  [
    {
      action: 'talk',
      text: 'Please say something'
    },
    {
      action: 'input',
      type: [ 'speech' ],
      eventUrl: ["#{request.base_url}/webhooks/asr"],
      speech: {
        endOnSilence: 1,
        uuid: [params[:uuid]],
        language: 'en-US'
      }
    }
  ].to_json
end

route :post, '/webhooks/asr' do
  [{
    action: 'talk',
    text: "You said #{params["speech"]["results"][0]["text"]}"
  }].to_json
end

route :post, '/webhooks/event' do
  puts params
end

set :port, 3000

View full source

Run your code

Save this file to your machine and run it:

ruby answer-inbound-call-with-asr.rb