app/text_to_speech.py

import os
import requests

SPEECH_REGION = os.environ.get("SPEECH_REGION")
SPEECH_KEY = os.environ.get("SPEECH_KEY")


def synthesize_ssml_to_speech(ssml, output_file_path):
    url = f"https://{SPEECH_REGION}.tts.speech.microsoft.com/cognitiveservices/v1"
    
    headers = {
      'Ocp-Apim-Subscription-Key': SPEECH_KEY,
      'Content-Type': 'application/ssml+xml',
      'X-Microsoft-OutputFormat': 'audio-16khz-128kbitrate-mono-mp3',
      'User-Agent': 'curl'
    }

    try:
        response = requests.request("POST", url, headers=headers, data=ssml.encode("utf-8"))
    
        if response.status_code == 200:
            with open(output_file_path, "wb") as f:
                f.write(response.content)
                print(f"Audio file saved as {output_file_path}")
        else:
            print(f"Request failed with status code: {response.status_code}")
            print(response.text)
    
    except requests.exceptions.RequestException as e:
        print("Request failed with an exception:")
        print(e)