Microsoft Azure 認知服務 – 語音 API

python quickstart.py

import azure.cognitiveservices.speech as speechsdk

# Creates an instance of a speech config with specified subscription key and service region.
# Replace with your own subscription key and service region (e.g., "westus").
speech_key, service_region = "39aca37122c049dfae2420933131f684", "westus"
speech_config = speechsdk.SpeechConfig(subscription=speech_key, region=service_region)

# Creates a recognizer with the given settings
speech_recognizer = speechsdk.SpeechRecognizer(speech_config=speech_config)

print("Say something...")


# Starts speech recognition, and returns after a single utterance is recognized. The end of a
# single utterance is determined by listening for silence at the end or until a maximum of 15
# seconds of audio is processed.  The task returns the recognition text as result. 
# Note: Since recognize_once() returns only a single utterance, it is suitable only for single
# shot recognition like command or query. 
# For long-running multi-utterance recognition, use start_continuous_recognition() instead.
result = speech_recognizer.recognize_once()

if ('hello' in result):
    print("hello")

# Checks result.
if result.reason == speechsdk.ResultReason.RecognizedSpeech:
    print("Recognized: {}".format(result.text))
elif result.reason == speechsdk.ResultReason.NoMatch:
    print("No speech could be recognized: {}".format(result.no_match_details))
elif result.reason == speechsdk.ResultReason.Canceled:
    cancellation_details = result.cancellation_details
    print("Speech Recognition canceled: {}".format(cancellation_details.reason))
    if cancellation_details.reason == speechsdk.CancellationReason.Error:
        print("Error details: {}".format(cancellation_details.error_details))

python TTSSample.py

'''
After you've set your subscription key, run this application from your working
directory with this command: python TTSSample.py
'''
import os, requests, time
from xml.etree import ElementTree
from playsound import playsound

# This code is required for Python 2.7
try: input = raw_input
except NameError: pass

'''
If you prefer, you can hardcode your subscription key as a string and remove
the provided conditional statement. However, we do recommend using environment
variables to secure your subscription keys. The environment variable is
set to SPEECH_SERVICE_KEY in our sample.

For example:
subscription_key = "Your-Key-Goes-Here"
'''

if 'SPEECH_SERVICE_KEY' in os.environ:
    subscription_key = os.environ['SPEECH_SERVICE_KEY']
else:
    print('Environment variable for your subscription key is not set.')
    exit()

class TextToSpeech(object):
    def __init__(self, subscription_key):
        self.subscription_key = subscription_key
        self.tts = input("What would you like to convert to speech: ")
        self.timestr = time.strftime("%Y%m%d-%H%M")
        self.access_token = None

    '''
    The TTS endpoint requires an access token. This method exchanges your
    subscription key for an access token that is valid for ten minutes.
    '''
    def get_token(self):
        fetch_token_url = "https://westus.api.cognitive.microsoft.com/sts/v1.0/issueToken"
        headers = {
            'Ocp-Apim-Subscription-Key': self.subscription_key
        }
        response = requests.post(fetch_token_url, headers=headers)
        self.access_token = str(response.text)

    def save_audio(self):
        base_url = 'https://westus.tts.speech.microsoft.com/'
        path = 'cognitiveservices/v1'
        constructed_url = base_url + path
        headers = {
            'Authorization': 'Bearer ' + self.access_token,
            'Content-Type': 'application/ssml+xml',
            'X-Microsoft-OutputFormat': 'riff-24khz-16bit-mono-pcm',
            'User-Agent': 'YOUR_RESOURCE_NAME'
        }
        xml_body = ElementTree.Element('speak', version='1.0')
        xml_body.set('{http://www.w3.org/XML/1998/namespace}lang', 'en-us')
        voice = ElementTree.SubElement(xml_body, 'voice')
        voice.set('{http://www.w3.org/XML/1998/namespace}lang', 'en-US')
        voice.set('name', 'en-US-Guy24kRUS') # Short name for 'Microsoft Server Speech Text to Speech Voice (en-US, Guy24KRUS)'
        voice.text = self.tts
        body = ElementTree.tostring(xml_body)

        response = requests.post(constructed_url, headers=headers, data=body)
        '''
        If a success response is returned, then the binary audio is written
        to file in your working directory. It is prefaced by sample and
        includes the date.
        '''
        if response.status_code == 200:
            with open('sample-001.wav', 'wb') as audio:
            #with open('sample-' + self.timestr + '.wav', 'wb') as audio:
                audio.write(response.content)
                print("\nStatus code: " + str(response.status_code) + "\nYour TTS is ready for playback.\n")
        else:
            print("\nStatus code: " + str(response.status_code) + "\nSomething went wrong. Check your subscription key and headers.\n")

if __name__ == "__main__":
    app = TextToSpeech(subscription_key)
    app.get_token()
    app.save_audio()
    playsound('sample-001.wav')