声音设计

Python

import os
import requests
import dashscope

# ======= 常量配置 =======
DEFAULT_TARGET_MODEL = "qwen3-tts-vd-2026-01-26"  # 声音设计、语音合成要使用相同的模型
DEFAULT_PREFERRED_NAME = "custom_voice"

# 声音描述：用自然语言描述期望的声音特质
VOICE_PROMPT = "年轻活泼的女性声音，语速较快，带有明显的上扬语调，适合介绍时尚产品。"


def create_voice_by_design(voice_prompt: str,
                           target_model: str = DEFAULT_TARGET_MODEL,
                           preferred_name: str = DEFAULT_PREFERRED_NAME) -> str:
    """
    通过声音描述创建音色，并返回 voice 参数
    """
    # 新加坡和北京地域的API Key不同。获取API Key：https://help.aliyun.com/zh/model-studio/get-api-key
    # 若没有配置环境变量，请用百炼API Key将下行替换为：api_key = "sk-xxx"
    api_key = os.getenv("DASHSCOPE_API_KEY")

    # 以下为北京地域url，若使用新加坡地域的模型，需将url替换为：https://dashscope-intl.aliyuncs.com/api/v1/services/audio/tts/customization
    url = "https://dashscope.aliyuncs.com/api/v1/services/audio/tts/customization"
    payload = {
        "model": "qwen-voice-design",
        "input": {
            "action": "create",
            "target_model": target_model,
            "preferred_name": preferred_name,
            "voice_prompt": voice_prompt,
            "preview_text": "大家好，欢迎来到我们的直播间！今天给大家推荐的这款产品真的超级好用。"
        },
        "parameters": {
            "sample_rate": 24000,
            "response_format": "wav"
        }
    }
    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"创建 voice 失败: {resp.status_code}, {resp.text}")

    result = resp.json()
    # 返回预览音频（可选：先试听确认效果）
    preview_audio = result.get("output", {}).get("preview_audio")
    if preview_audio:
        import base64
        audio_data = base64.b64decode(preview_audio["data"])
        with open("preview_audio.wav", "wb") as f:
            f.write(audio_data)
        print(f"预览音频已保存到 preview_audio.wav ({len(audio_data)} bytes)")

    try:
        return result["output"]["voice"]
    except (KeyError, ValueError) as e:
        raise RuntimeError(f"解析 voice 响应失败: {e}")


if __name__ == '__main__':
    # 以下为北京地域url，若使用新加坡地域的模型，需将url替换为：https://dashscope-intl.aliyuncs.com/api/v1
    dashscope.base_http_api_url = 'https://dashscope.aliyuncs.com/api/v1'

    voice_id = create_voice_by_design(VOICE_PROMPT)
    print(f"创建的音色ID: {voice_id}")

    text = "大家好，欢迎来到我们的直播间！今天给大家推荐的这款产品真的超级好用。"
    response = dashscope.MultiModalConversation.call(
        model=DEFAULT_TARGET_MODEL,
        # 新加坡和北京地域的API Key不同。获取API Key：https://help.aliyun.com/zh/model-studio/get-api-key
        # 若没有配置环境变量，请用百炼API Key将下行替换为：api_key = "sk-xxx"
        api_key=os.getenv("DASHSCOPE_API_KEY"),
        text=text,
        voice=voice_id,
        stream=False
    )
    print(response)

cURL

步骤一：通过声音描述创建音色

curl -X POST 'https://dashscope.aliyuncs.com/api/v1/services/audio/tts/customization' \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H 'Content-Type: application/json' \
-d '{
    "model": "qwen-voice-design",
    "input": {
        "action": "create",
        "target_model": "qwen3-tts-vd-2026-01-26",
        "preferred_name": "custom_voice",
        "voice_prompt": "年轻活泼的女性声音，语速较快，带有明显的上扬语调，适合介绍时尚产品。",
        "preview_text": "大家好，欢迎来到我们的直播间！今天给大家推荐的这款产品真的超级好用。"
    },
    "parameters": {
        "sample_rate": 24000,
        "response_format": "wav"
    }
}'

步骤二：使用设计音色合成语音

将 YOUR_VOICE_ID 替换为上一步返回的 voice 值。

curl -X POST 'https://dashscope.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，欢迎来到我们的直播间！今天给大家推荐的这款产品真的超级好用。",
        "voice": "YOUR_VOICE_ID"
    }
}'