声音设计

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
  """
  api_key = os.getenv("DASHSCOPE_API_KEY")

  url = "https://dashscope.aliyuncs.com/api/v1/services/audio/tts/customization"
  payload = {
    "model": "qwen-voice-enrollment",  # 不要修改该值
    "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"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:
    print(f"预览音频URL: {preview_audio}")

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


if __name__ == '__main__':
  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,
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    text=text,
    voice=voice_id,
    stream=False
  )
  print(response)

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": "voice-enrollment",
  "input": {
    "action": "create_voice",
    "target_model": "cosyvoice-v3-plus",
    "voice_prompt": "沉稳的中年男性播音员，音色低沉浑厚，富有磁性，语速平稳，吐字清晰，适合用于新闻播报或纪录片解说。",
    "preview_text": "各位听众朋友，大家好，欢迎收听晚间新闻。",
    "prefix": "announcer",
    "language_hints": ["zh"]
  },
  "parameters": {
    "sample_rate": 24000,
    "response_format": "wav"
  }
}'

# 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/audio/tts/SpeechSynthesizer \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
  "model": "cosyvoice-v3-plus",
  "input": {
    "text": "各位听众朋友，大家好，欢迎收听晚间新闻。",
    "voice": "YOUR_VOICE_ID",
    "format": "wav",
    "sample_rate": 24000
  }
}'