import os
import requests
import base64
import pathlib
import dashscope


DEFAULT_TARGET_MODEL = "qwen3-tts-vc-2026-01-22"
DEFAULT_PREFERRED_NAME = "guanyu"
DEFAULT_AUDIO_MIME_TYPE = "audio/mpeg"
VOICE_FILE_PATH = "voice.mp3"


def create_voice(file_path: str,
                 target_model: str = DEFAULT_TARGET_MODEL,
                 preferred_name: str = DEFAULT_PREFERRED_NAME,
                 audio_mime_type: str = DEFAULT_AUDIO_MIME_TYPE) -> str:
    api_key = os.getenv("DASHSCOPE_API_KEY")

    file_path_obj = pathlib.Path(file_path)
    if not file_path_obj.exists():
        raise FileNotFoundError(f"The audio file does not exist: {file_path}")

    base64_str = base64.b64encode(file_path_obj.read_bytes()).decode()
    data_uri = f"data:{audio_mime_type};base64,{base64_str}"

    url = "https://[workspace-id].ap-southeast-1.maas.aliyuncs.com/api/v1/services/audio/tts/customization"
    payload = {
        "model": "qwen-voice-enrollment",
        "input": {
            "action": "create",
            "target_model": target_model,
            "preferred_name": preferred_name,
            "audio": {"data": data_uri}
        }
    }
    headers = {
        "Authorization": f"Bearer {api_key}",
        "Content-Type": "application/json"
    }

    resp = requests.post(url, json=payload, headers=headers)
    if resp.status_code != 200:
        raise RuntimeError(f"create voice failed: {resp.status_code}, {resp.text}")

    try:
        return resp.json()["output"]["voice"]
    except (KeyError, ValueError) as e:
        raise RuntimeError(f"failed: {e}")


if __name__ == '__main__':
    dashscope.base_http_api_url = 'https://[workspace-id].ap-southeast-1.maas.aliyuncs.com/api/v1'

    text = "How is the weather today?"
    
    response = dashscope.MultiModalConversation.call(
        model=DEFAULT_TARGET_MODEL,
        api_key=os.getenv("DASHSCOPE_API_KEY"),
        text=text,
        voice=create_voice(VOICE_FILE_PATH),
        stream=False
    )
    print(response)