gTTS.py

import os

os.environ["GOOGLE_APPLICATION_CREDENTIALS"] = "config/mamliKey.json"

def synthesize_text(text,gender):
    """Synthesizes speech from the input string of text."""
    from google.cloud import texttospeech

    client = texttospeech.TextToSpeechClient()
    voice = "en-IN-Wavenet-" + gender
    input_text = texttospeech.SynthesisInput(text=text)
    # Note: the voice can also be specified by name.
    # Names of voices can be retrieved with client.list_voices().
    voice = texttospeech.VoiceSelectionParams(
        language_code="en-IN",
        name=voice,
    )

    audio_config = texttospeech.AudioConfig(
        audio_encoding=texttospeech.AudioEncoding.MP3,
        speaking_rate=0.80,
    )

    response = client.synthesize_speech(
        request={"input": input_text, "voice": voice, "audio_config": audio_config}
    )

    # The response's audio_content is binary.
    with open("inputs/audio.wav", "wb") as out:
        out.write(response.audio_content)