Why even use the entire SDK lul...

gtts.py

import base64
import json
import requests


class TTSException(Exception):

    def __init__(self, code: int, message: str, status: str):
        self.code = code
        self.message = message
        self.status = status


class TextToSpeech(object):

    def __init__(self, api_key: str, audio_config: dict = {"audioEncoding": "MP3"}):
        self.api_key = api_key
        self.audio_config = audio_config

    def create_voice(self, language: str = "en-US", type: str = "Standard-A", gender: str = "FEMALE"):
        return {
            "languageCode": language,
            "name": "%s-%s" % (language, type),
            "ssmlGender": gender.upper()
        }

    def get_audio(self, text: str, voice: dict = {"languageCode": "en-US", "name": "en-US-Standard-A", "ssmlGender": "FEMALE"}):
        r = requests.post(
            url="https://texttospeech.googleapis.com/v1/text:synthesize",
            json={
                "input": {"text": text},
                "voice": voice,
                "audioConfig": self.audio_config
            },
            headers={
                "X-Goog-Api-Key": self.api_key,
                "Content-Type": "application/json; charset=utf-8"
            }
        )

        data = r.json()

        if r.status_code != 200 and "error" in data:
            error = data["error"]
            raise TTSException(error["code"], error["message"], error["status"]) 
        
        return base64.b64decode(data["audioContent"])