Blog

Develop natural language solutions in Azure​

Lab

Recognize and synthesize speech

Code 1

from dotenv import load_dotenv
from datetime import datetime
import os

# Import namespaces
# Import namespaces
from azure.core.credentials import AzureKeyCredential
import azure.cognitiveservices.speech as speech_sdk

def main():

    # Clear the console
    os.system('cls' if os.name=='nt' else 'clear')

    try:
        global speech_config

        # Get config settings
        load_dotenv()
        speech_key = os.getenv('KEY')
        speech_region = os.getenv('REGION')

        # Configure speech service
        # Configure speech service
        speech_config = speech_sdk.SpeechConfig(speech_key, speech_region)
        print('Ready to use speech service in:', speech_config.region)

        # Get spoken input
        command = TranscribeCommand()
        if command.lower() == 'what time is it?':
            TellTime()

    except Exception as ex:
        print(ex)

def TranscribeCommand():
    command = ''

    # Configure speech recognition
    # Configure speech recognition
    current_dir = os.getcwd()
    audioFile = current_dir + '/time.wav'
    audio_config = speech_sdk.AudioConfig(filename=audioFile)
    speech_recognizer = speech_sdk.SpeechRecognizer(speech_config, audio_config)

    # Process speech input
    # Process speech input
    print("Listening...")
    speech = speech_recognizer.recognize_once_async().get()
    if speech.reason == speech_sdk.ResultReason.RecognizedSpeech:
        command = speech.text
        print(command)
    else:
        print(speech.reason)
        if speech.reason == speech_sdk.ResultReason.Canceled:
            cancellation = speech.cancellation_details
            print(cancellation.reason)
            print(cancellation.error_details)

    # Return the command
    return command


def TellTime():
    now = datetime.now()
    response_text = 'The time is {}:{:02d}'.format(now.hour,now.minute)


    # Configure speech synthesis
    # Configure speech synthesis
    output_file = "output.wav"
    speech_config.speech_synthesis_voice_name = "en-GB-RyanNeural"
    audio_config = speech_sdk.audio.AudioConfig(filename=output_file)
    speech_synthesizer = speech_sdk.SpeechSynthesizer(speech_config, audio_config,)

    # Synthesize spoken output
    # Synthesize spoken output
    speak = speech_synthesizer.speak_text_async(response_text).get()
    if speak.reason != speech_sdk.ResultReason.SynthesizingAudioCompleted:
        print(speak.reason)
    else:
        print("Spoken output saved in " + output_file)

    # Print the response
    print(response_text)


if __name__ == "__main__":
    main()

Code 2:

from dotenv import load_dotenv
from datetime import datetime
import os

# Import namespaces
# Import namespaces
from azure.core.credentials import AzureKeyCredential
import azure.cognitiveservices.speech as speech_sdk

def main():

    # Clear the console
    os.system('cls' if os.name=='nt' else 'clear')

    try:
        global speech_config

        # Get config settings
        load_dotenv()
        speech_key = os.getenv('KEY')
        speech_region = os.getenv('REGION')

        # Configure speech service
        # Configure speech service
        speech_config = speech_sdk.SpeechConfig(speech_key, speech_region)
        print('Ready to use speech service in:', speech_config.region)

        # Get spoken input
        command = TranscribeCommand()
        if command.lower() == 'what time is it?':
            TellTime()

    except Exception as ex:
        print(ex)

def TranscribeCommand():
    command = ''

    # Configure speech recognition
    # Configure speech recognition
    current_dir = os.getcwd()
    audioFile = current_dir + '/time.wav'
    audio_config = speech_sdk.AudioConfig(filename=audioFile)
    speech_recognizer = speech_sdk.SpeechRecognizer(speech_config, audio_config)

    # Process speech input
    # Process speech input
    print("Listening...")
    speech = speech_recognizer.recognize_once_async().get()
    if speech.reason == speech_sdk.ResultReason.RecognizedSpeech:
        command = speech.text
        print(command)
    else:
        print(speech.reason)
        if speech.reason == speech_sdk.ResultReason.Canceled:
            cancellation = speech.cancellation_details
            print(cancellation.reason)
            print(cancellation.error_details)

    # Return the command
    return command


def TellTime():
    now = datetime.now()
    response_text = 'The time is {}:{:02d}'.format(now.hour,now.minute)


    # Configure speech synthesis
    # Configure speech synthesis
    output_file = "output.wav"
    speech_config.speech_synthesis_voice_name = "en-GB-RyanNeural"
    audio_config = speech_sdk.audio.AudioConfig(filename=output_file)
    speech_synthesizer = speech_sdk.SpeechSynthesizer(speech_config, audio_config,)

    # Synthesize spoken output


    # Print the response
    print(response_text)


if __name__ == "__main__":
    main()

analyze text lab

code:

from dotenv import load_dotenv
import os

# Import namespaces
# import namespaces
from azure.core.credentials import AzureKeyCredential
from azure.ai.textanalytics import TextAnalyticsClient

def main():
    try:
        # Get Configuration Settings
        load_dotenv()
        ai_endpoint = os.getenv('AI_SERVICE_ENDPOINT')
        ai_key = os.getenv('AI_SERVICE_KEY')

        # Create client using endpoint and key
        # Create client using endpoint and key
        credential = AzureKeyCredential(ai_key)
        ai_client = TextAnalyticsClient(endpoint=ai_endpoint, credential=credential)

        # Analyze each text file in the reviews folder
        reviews_folder = 'reviews'
        for file_name in os.listdir(reviews_folder):
            # Read the file contents
            print('\n-------------\n' + file_name)
            text = open(os.path.join(reviews_folder, file_name), encoding='utf8').read()
            print('\n' + text)

            # Get language
            # Get language
            detectedLanguage = ai_client.detect_language(documents=[text])[0]
            print('\nLanguage: {}'.format(detectedLanguage.primary_language.name))

            # Get sentiment
            # Get sentiment
            sentimentAnalysis = ai_client.analyze_sentiment(documents=[text])[0]
            print("\nSentiment: {}".format(sentimentAnalysis.sentiment))

            # Get key phrases
            # Get key phrases
            phrases = ai_client.extract_key_phrases(documents=[text])[0].key_phrases
            if len(phrases) > 0:
                print("\nKey Phrases:")
                for phrase in phrases:
                    print('\t{}'.format(phrase))

            # Get entities
            # Get entities
            entities = ai_client.recognize_entities(documents=[text])[0].entities
            if len(entities) > 0:
                print("\nEntities")
                for entity in entities:
                    print('\t{} ({})'.format(entity.text, entity.category))

            # Get linked entities
            # Get linked entities
            entities = ai_client.recognize_linked_entities(documents=[text])[0].entities
            if len(entities) > 0:
                print("\nLinks")
                for linked_entity in entities:
                    print('\t{} ({})'.format(linked_entity.name, linked_entity.url))


    except Exception as ex:
        print(ex)


if __name__ == "__main__":
    main()