audio_utils.py

import base64
import os
from typing import Literal

import requests
from gtts import gTTS


def text_to_speech(
    text, language: Literal["de", "en"] = "de", save_path: str = "output.mp3"
):
    tts = gTTS(text=text, lang=language, slow=False)
    tts.save(save_path)


LANG_TO_VOICE_MAPPING = {
    "de": "Vicki",
    "en": "Joanna",
}


POLLY_URL = os.environ["POLLY_URL"]
POLLY_KEY = os.environ["POLLY_KEY"]


def text_to_speech_polly(
    text, language: Literal["de", "en"] = "de", save_path: str = "output.mp3"
):
    json_data = {
        "text": text,
        "voice": LANG_TO_VOICE_MAPPING.get(language, "Joanna"),
        "prefered_engine": "neural",
        "code": POLLY_KEY,
    }

    response = requests.post(POLLY_URL, json=json_data)

    try:
        response.raise_for_status()
    except requests.exceptions.HTTPError as error:
        print(error)
        print(response.text)
        return

    binary_data = base64.b64decode(response.content)

    with open(save_path, "wb") as f:
        f.write(binary_data)