Time to Speak Some Dialects, Qwen-TTS!

import os
import requests
import dashscope


def get_api_key():
    api_key = os.getenv("DASHSCOPE_API_KEY")
    if not api_key:
        raise EnvironmentError("DASHSCOPE_API_KEY environment variable not set.")
    return api_key


def synthesize_speech(text, voice="Dylan", model="qwen-tts-latest"):
    api_key = get_api_key()
    try:
        response = dashscope.audio.qwen_tts.SpeechSynthesizer.call(
            model=model,
            api_key=api_key,
            text=text,
            voice=voice,
        )
        
        # Check if response is None
        if response is None:
            raise RuntimeError("API call returned None response")
        
        # Check if response.output is None
        if response.output is None:
            raise RuntimeError("API call failed: response.output is None")
        
        # Check if response.output.audio exists
        if not hasattr(response.output, 'audio') or response.output.audio is None:
            raise RuntimeError("API call failed: response.output.audio is None or missing")
        
        audio_url = response.output.audio["url"]
        return audio_url
    except Exception as e:
        raise RuntimeError(f"Speech synthesis failed: {e}")


def download_audio(audio_url, save_path):
    try:
        resp = requests.get(audio_url, timeout=10)
        resp.raise_for_status()
        with open(save_path, 'wb') as f:
            f.write(resp.content)
        print(f"Audio file saved to: {save_path}")
    except Exception as e:
        raise RuntimeError(f"Download failed: {e}")


def main():
    text = (
        """哟，您猜怎么着？今儿个我看NBA，库里投篮跟闹着玩似的，张手就来，篮筐都得喊他“亲爹”了"""
    )
    save_path = "downloaded_audio.wav"
    try:
        audio_url = synthesize_speech(text)
        download_audio(audio_url, save_path)
    except Exception as e:
        print(e)


if __name__ == "__main__":
    main()