Calling the Google Text To Speech API

google_text_to_speech.py

def text_to_speech(speak, languageCode, outputFilePath, speed=1.0):
    """Synthesizes speech from the input string of text or ssml.

    Note: ssml must be well-formed according to:
        https://www.w3.org/TR/speech-synthesis/
    """
    from google.cloud import texttospeech

    # Instantiates a client
    client = texttospeech.TextToSpeechClient()

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

    # Build the voice request, select the language code ("en-US") and the ssml
    # voice gender ("neutral")
    voice = texttospeech.VoiceSelectionParams(
        language_code=languageCode, ssml_gender=texttospeech.SsmlVoiceGender.MALE
    )

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

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

    # The response's audio_content is binary.
    with open(outputFilePath, "wb") as out:
        # Write the response to the output file.
        out.write(response.audio_content)
        print('Audio content written to file "{}"'.format(outputFilePath))