Voice - Play audio and perform automatic speech recognition

from base64 import b64encode

import requests

customer_id = 'Your Customer ID goes here.'
api_key = 'Your API key goes here.'

destination_number = 'The complete phone number you want to call, including country code, with no special characters or spaces.'
caller_id_number = 'The phone number you purchased from Telesign goes here.'
external_id = 'An external ID you generated for this transaction.' # Optional parameter

url = "https://rest-ww.telesign.com/v2/voice"

payload = {
            "jsonrpc": "2.0",
            "method": "dial",
            "params": {
                "to": destination_number,
                "caller_id_number": caller_id_number,
                "external_id": external_id
            }
    }


headers = {
    'Accept': "application/json",
    'Content-Type': "application/json",
    'Authorization': "Basic {}".format(b64encode(customer_id + ":" + api_key).decode('utf-8')),
    }

response = requests.request("POST", url, data=json.dumps(payload), headers=headers)

print(response.text)

{
  "method": "speak",
  "params": {
    "tts": {
      "message": "<speak>Press <prosody volume='loud'>1</prosody> for your account balance. Press <prosody volume='loud'>2</prosody> to speak with a customer service representative.</speak>",
      "language": "en-US",
      "type": "ssml"
    },
    "detect_speech": {
        "timeout": 5000,
        "inter_speech_timeout": 3000,
        "max_speech_duration": 10000,
        "language": "en-US"
    }
  }
}

from json import dumps, loads
from bottle import route, run, request, post
# This is an example response to a dial_completed event that will play a message and detect speech from an end user.
# {
#   "method": "speak",
#   "params": {
#     "tts": {
#       "message": "<speak>Say <prosody volume='loud'>1</prosody> for your account balance. Say <prosody volume='loud'>2</prosody> to speak with a customer service representative.</speak>",
#       "language": "en-US",
#       "type": "ssml"
#     },
#     "detect_speech": {
#         "timeout": 5000,
#         "inter_speech_timeout": 3000,
#         "max_speech_duration": 10000,
#         "language": "en-US"
#     }
#   }
# }

class Response:
    def __init__(self, method, params=None):
        if params is None:
            params = {}
        self.json_rpc = "2.0"
        self.method = method
        self.params = params
    def to_json(self):
        return dumps(self.__dict__)

@post('/')
def telesign_event():
    # Throughout a call session Telesign will notify you of all events.
    # Each event requires you to send us an appropriate action defined in our documentation.
    # This endpoint needs to match the URL stored in our system to properly communicate.
    #
    # In this example, the server will respond to the dial_completed event.
    # First extract the event from the JSON body in the request.
    event = request.json.get('event')
    if event == 'dial_completed':
        # Check for an 'answered' status. For 'answered' fill out your parameters:
        message = "<speak>Say <prosody volume='loud'>1</prosody> for your account balance. Say <prosody volume='loud'>2</prosody> to speak with a customer service representative.</speak>"
        language = "en-US"
        timeout = 10000 # How long to wait for speech from the user before ending recognition.
        inter_speech_timeout = 3000 # How long to wait for the next utterance before ending recognition, after at least one utterance has been spoken.
        max_speech_duration = 10000 # How long to wait for the whole voice recognition.

        # Generate the command in the JSON format.
        return Response(method='speak',
          params={
            'tts': { 'message': message, 'language': language },
            'detect_speech': { 'timeout': timeout, 'inter_speech_timeout': inter_speech_timeout, 'max_speech_duration': max_speech_duration }
          }
        ).to_json()
    else:
        return Response(method='hangup').to_json()

run(host='localhost', port=8080, debug=True)