speech_translation.py

import os
import azure.cognitiveservices.speech as speechsdk

def recognize_from_microphone():
    # This example requires environment variables named "SPEECH_KEY" and "SPEECH_REGION"
    speech_translation_config = speechsdk.translation.SpeechTranslationConfig(subscription=os.environ.get('SPEECH_KEY'), region=os.environ.get('SPEECH_REGION'))
    speech_translation_config.speech_recognition_language="en-US"

    target_language1="no"
    speech_translation_config.add_target_language(target_language1)

    target_language2="fr"
    speech_translation_config.add_target_language(target_language2)

    audio_config = speechsdk.audio.AudioConfig(use_default_microphone=True)
    translation_recognizer = speechsdk.translation.TranslationRecognizer(translation_config=speech_translation_config, audio_config=audio_config)

    print("Speak into your microphone.")
    translation_recognition_result = translation_recognizer.recognize_once_async().get()

    if translation_recognition_result.reason == speechsdk.ResultReason.TranslatedSpeech:
        print("Recognized: {}".format(translation_recognition_result.text))
        print("""Translated into '{}': {}""".format(
            target_language1, 
            translation_recognition_result.translations[target_language1]))
        print("""Translated into '{}': {}""".format(
            target_language2, 
            translation_recognition_result.translations[target_language2]))
    elif translation_recognition_result.reason == speechsdk.ResultReason.NoMatch:
        print("No speech could be recognized: {}".format(translation_recognition_result.no_match_details))
    elif translation_recognition_result.reason == speechsdk.ResultReason.Canceled:
        cancellation_details = translation_recognition_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))
            print("Did you set the speech resource key and region values?")


    speech_config = speechsdk.SpeechConfig(subscription=os.environ.get('SPEECH_KEY'), region=os.environ.get('SPEECH_REGION'))
    audio_config = speechsdk.audio.AudioOutputConfig(use_default_speaker=True)

    # The neural multilingual voice can speak different languages based on the input text.
    speech_config.speech_synthesis_voice_name='en-US-AvaMultilingualNeural'

    speech_synthesizer = speechsdk.SpeechSynthesizer(speech_config=speech_config, audio_config=audio_config)

    speech_synthesis_result = speech_synthesizer.speak_text_async(translation_recognition_result.translations[target_language1]).get()

    if speech_synthesis_result.reason == speechsdk.ResultReason.SynthesizingAudioCompleted:
        print("Speech synthesized for text [{}]".format(text))
    elif speech_synthesis_result.reason == speechsdk.ResultReason.Canceled:
        cancellation_details = speech_synthesis_result.cancellation_details
        print("Speech synthesis canceled: {}".format(cancellation_details.reason))
        if cancellation_details.reason == speechsdk.CancellationReason.Error:
            if cancellation_details.error_details:
                print("Error details: {}".format(cancellation_details.error_details))
                print("Did you set the speech resource key and region values?")


recognize_from_microphone()