Initial commit

{\rtf1\ansi\ansicpg1252\cocoartf1038\cocoasubrtf350

{\fonttbl\f0\fswiss\fcharset0 Helvetica;}

{\colortbl;\red255\green255\blue255;}

\margl1440\margr1440\vieww9000\viewh8400\viewkind0

\pard\tx720\tx1440\tx2160\tx2880\tx3600\tx4320\tx5040\tx5760\tx6480\tx7200\tx7920\tx8640\ql\qnatural\pardirnatural

\f0\fs24 \cf0 No work files for this lesson...}

 No newline at end of file

{\rtf1\ansi\ansicpg1252\cocoartf1038\cocoasubrtf350

{\fonttbl\f0\fswiss\fcharset0 Helvetica;}

{\colortbl;\red255\green255\blue255;}

\margl1440\margr1440\vieww9000\viewh8400\viewkind0

\pard\tx720\tx1440\tx2160\tx2880\tx3600\tx4320\tx5040\tx5760\tx6480\tx7200\tx7920\tx8640\ql\qnatural\pardirnatural

\f0\fs24 \cf0 No work files for this lesson...}

 No newline at end of file

'''

    Example Python script for calling the IBM Watson Speech to Text API

    You will need to provide your own IBM Watson service credentials.

    This script is provided as-is, with no warranties explicit or implied.

    You may use this script for education or professional purposes, and no

    attribution is required.

    Matt Coatney

    O'Reilly Media

    Copyright (c) 2017

'''

import os, subprocess, requests, codecs, json, sys

from requests.auth import HTTPBasicAuth

def speech_to_text(audiofile, username, password):

    f = open(audiofile, 'rb')

    data = f.read()

    f.close()

    auth = HTTPBasicAuth(username, password)

    res = requests.post(url='https://stream.watsonplatform.net/speech-to-text/api/v1/recognize?continuous=true',

                        data=data,

                        auth=auth,

                        headers={'Content-Type': 'audio/ogg; codecs=opus'})

    return res.json()

if len(sys.argv) < 4:

    print 'Usage: python ' + sys.argv[0] + ' path_to_file api_username api_password'

path = sys.argv[1]

username = sys.argv[2]

password = sys.argv[3]

# Get audio track and convert to compressed OGG format - requires ffmpeg to be installed

command = 'ffmpeg -i "' + path + '" -y -loglevel error -ab 160k -ac 2 -ar 16000 -vn "' + path + '.ogg"'

subprocess.call(command, shell=True)        

# Call API

result = speech_to_text(path + '.ogg', username, password)

text = ''

for piece in result['results']:

    text += piece['alternatives'][0]['transcript'].replace('%HESITATION', '')

# Write results

f = codecs.open(path + '.s2t.json', mode='w', encoding='utf8')

f.write(json.dumps(result, indent=4, separators=(',', ': ')))

f.close()

f = codecs.open(path + '.txt', mode='w', encoding='utf8')

f.write(text)

f.close()

 No newline at end of file

'''

    Example Python script for calling the IBM Watson Text to Speech API

    You will need to provide your own IBM Watson service credentials.

    This script is provided as-is, with no warranties explicit or implied.

    You may use this script for education or professional purposes, and no

    attribution is required.

    Matt Coatney

    O'Reilly Media

    Copyright (c) 2017

'''

import json, requests, codecs, sys, time

from requests.auth import HTTPBasicAuth

def text_to_speech(text, username, password):

    time.sleep(1) # Throttle multiple calls

    url_base = 'https://stream.watsonplatform.net/text-to-speech/api/v1/synthesize?voice=en-US_MichaelVoice'

    data = json.dumps( { 'text': text.encode('UTF-8') } )

    auth = HTTPBasicAuth(username, password)

    headers = {

      'Content-Type': 'application/json;charset=utf-8',

      'Accept': 'audio/wav'

    }

    res = requests.post(url_base, data=data, auth=auth, headers=headers)

    return res.content

if len(sys.argv) < 4:

    print 'Usage: python ' + sys.argv[0] + ' path_to_file api_username api_password'

path = sys.argv[1]

username = sys.argv[2]

password = sys.argv[3]

# Get text from file

f = codecs.open(path, mode='r', encoding='utf8')

text = f.read()

f.close()

# Call API

result = text_to_speech(text, username, password)

# Write results

f = open(path + '.t2s.wav', 'wb')

f.write(result)

f.close()

 No newline at end of file