Alibaba Cloud Model Studio：聲音設計

Python

import os
import requests
import dashscope

# ======= 常量配置 =======
DEFAULT_TARGET_MODEL = "qwen3-tts-vd-2026-01-26"  # 聲音設計、語音合成要使用相同的模型
DEFAULT_PREFERRED_NAME = "custom_voice"

# 聲音描述：用自然語言描述期望的聲音特質
VOICE_PROMPT = "年輕活潑的女性聲音，語速較快，帶有明顯的上揚語調，適合介紹時尚產品。"


def create_voice_by_design(voice_prompt: str,
                           target_model: str = DEFAULT_TARGET_MODEL,
                           preferred_name: str = DEFAULT_PREFERRED_NAME) -> str:
    """
    通過聲音描述建立音色，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")

    # 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,
            "voice_prompt": voice_prompt
        }
    }
    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}")

    result = resp.json()
    preview_audio = result.get("output", {}).get("preview_audio")
    if preview_audio:
        print(f"預覽音頻URL: {preview_audio}")

    try:
        return result["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'

    voice_id = create_voice_by_design(VOICE_PROMPT)
    print(f"建立的音色ID: {voice_id}")

    text = "大家好，歡迎來到我們的直播間！今天給大家推薦的這款產品真的超級好用。"
    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=voice_id,
        stream=False
    )
    print(response)

cURL

步驟一：通過聲音描述建立音色

# 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

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-vd-2026-01-26",
        "preferred_name": "custom_voice",
        "voice_prompt": "年輕活潑的女性聲音，語速較快，帶有明顯的上揚語調，適合介紹時尚產品。"
    }
}'

步驟二：使用設計音色合成語音

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-vd-2026-01-26",
    "input": {
        "text": "大家好，歡迎來到我們的直播間！今天給大家推薦的這款產品真的超級好用。",
        "voice": "YOUR_VOICE_ID"
    }
}'