Alibaba Cloud Model Studio：聲音複刻

Python

import os
import requests
import base64
import pathlib
import dashscope

# ======= 常量配置 =======
DEFAULT_TARGET_MODEL = "qwen3-tts-vc-2026-01-22"  # 聲音複刻、語音合成要使用相同的模型
DEFAULT_PREFERRED_NAME = "guanyu"
DEFAULT_AUDIO_MIME_TYPE = "audio/mpeg"
VOICE_FILE_PATH = "voice.mp3"  # 用於聲音複刻的本地音頻檔案的相對路徑


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:
    """
    建立音色，並返回 voice 參數
    """
    # 新加坡地區和北京地區的API Key不同。擷取API Key：https://www.alibabacloud.com/help/zh/model-studio/get-api-key
    # 若沒有配置環境變數，請用百鍊API Key將下行替換為：api_key = "sk-xxx"
    api_key = os.getenv("DASHSCOPE_API_KEY")

    file_path_obj = pathlib.Path(file_path)
    if not file_path_obj.exists():
        raise FileNotFoundError(f"音頻檔案不存在: {file_path}")

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

    # 以下為新加坡地區url，若使用北京地區的模型，需將url替換為：https://dashscope.aliyuncs.com/api/v1/services/audio/tts/customization
    url = "https://dashscope-intl.aliyuncs.com/api/v1/services/audio/tts/customization"
    payload = {
        "model": "qwen-voice-enrollment", # 不要修改該值
        "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"建立 voice 失敗: {resp.status_code}, {resp.text}")

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


if __name__ == '__main__':
    # 以下為新加坡地區url，若使用北京地區的模型，需將url替換為：https://dashscope.aliyuncs.com/api/v1
    dashscope.base_http_api_url = 'https://dashscope-intl.aliyuncs.com/api/v1'

    text = "今天天氣怎麼樣？"
    response = dashscope.MultiModalConversation.call(
        model=DEFAULT_TARGET_MODEL,
        # 新加坡地區和北京地區的API Key不同。擷取API Key：https://www.alibabacloud.com/help/zh/model-studio/get-api-key
        # 若沒有配置環境變數，請用百鍊API Key將下行替換為：api_key = "sk-xxx"
        api_key=os.getenv("DASHSCOPE_API_KEY"),
        text=text,
        voice=create_voice(VOICE_FILE_PATH), # 將voice參數替換為複刻產生的專屬音色
        stream=False
    )
    print(response)

cURL

通過 cURL 進行聲音複刻分為兩步：先建立音色，再用該音色合成語音。

步驟一：建立音色

# 將 voice.mp3 替換為實際音頻檔案路徑
# 以下為新加坡地區url，若使用北京地區的模型，需將url替換為：https://dashscope.aliyuncs.com/api/v1/services/audio/tts/customization
# 新加坡地區和北京地區的API Key不同。擷取API Key：https://www.alibabacloud.com/help/zh/model-studio/get-api-key

AUDIO_BASE64=$(base64 -i voice.mp3)

curl -X POST 'https://dashscope-intl.aliyuncs.com/api/v1/services/audio/tts/customization' \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H 'Content-Type: application/json' \
-d '{
    "model": "qwen-voice-enrollment",
    "input": {
        "action": "create",
        "target_model": "qwen3-tts-vc-2026-01-22",
        "preferred_name": "guanyu",
        "audio": {"data": "data:audio/mpeg;base64,'$AUDIO_BASE64'"}
    }
}'

步驟二：使用複刻音色合成語音

將上一步返回的voice值填入以下請求中。

# 將 YOUR_VOICE_ID 替換為上一步返回的 voice 值
# 以下為新加坡地區url，若使用北京地區的模型，需將url替換為：https://dashscope.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation

curl -X POST 'https://dashscope-intl.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation' \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H 'Content-Type: application/json' \
-d '{
    "model": "qwen3-tts-vc-2026-01-22",
    "input": {
        "text": "今天天氣怎麼樣？",
        "voice": "YOUR_VOICE_ID"
    }
}'