create_audio.py

def create_audio(text, language='ko-KR'):

  # Instantiates a client
  client = texttospeech.TextToSpeechClient()

  # Set the text input to be synthesized
  synthesis_input = texttospeech.types.SynthesisInput(text=text)

  # Build the voice request, select the language code ("en-US") and the ssml
  # voice gender ("neutral")
  voice = texttospeech.types.VoiceSelectionParams(
    language_code='ko-KR',
    ssml_gender=texttospeech.enums.SsmlVoiceGender.NEUTRAL)

  # Select the type of audio file you want returned
  audio_config = texttospeech.types.AudioConfig(
    audio_encoding=texttospeech.enums.AudioEncoding.MP3)

  # Perform the text-to-speech request on the text input with the selected
  # voice parameters and audio file type
  response = client.synthesize_speech(synthesis_input, voice, audio_config)

  # The response's audio_content is binary.
  with open('audio/{}.mp3'.format(text), 'wb') as out:
    # Write the response to the output file.
    out.write(response.audio_content)