text_to_speech.rb

def convert_to_audio(text, gender)
    client = Google::Cloud::TextToSpeech.text_to_speech

    input_text = { text: text }

    # Note: the voice can also be specified by name.
    # Names of voices can be retrieved with client.list_voices
    # https://cloud.google.com/text-to-speech/docs/voices
    if gender == 'MALE'
      name = 'en-US-Standard-D'
    else
      name = 'en-US-Standard-E'
    end
    voice = {
      language_code: "en-US",
      name: name,
      ssml_gender:   gender
    }

    audio_config = { audio_encoding: "MP3" }

    response = client.synthesize_speech(
      input: input_text,
      voice: voice,
      audio_config: audio_config
    )

    # Need something here to catch the errors that Google sometimes sends, and then re-run the synthesize_speech function, possible after a short pause

    return response
  end