声音定制

查询音色列表

分页查询账号下的声音列表。

POST

/services/audio/tts/customization

cURL

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": "list",
    "page_size": 10,
    "page_index": 0
  }
}'

{
  "output": {
    "page_index": 0,
    "page_size": 10,
    "total_count": 26,
    "voice_list": [
      {
        "voice": "qwen-tts-vd-announcer-voice-20251210170454-a1b2",
        "target_model": "qwen3-tts-vd-realtime-2026-01-15",
        "language": "en",
        "voice_prompt": "A composed middle-aged male announcer with a deep, rich and magnetic voice.",
        "preview_text": "Dear listeners, hello everyone. Welcome to the evening news.",
        "gmt_create": "2025-12-10 17:04:54",
        "gmt_modified": "2025-12-10 17:04:54"
      }
    ]
  },
  "usage": {},
  "request_id": "xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

鉴权

string

header

必填

千问云 API Key。详见获取 API Key。

请求体

application/json

enum<string>

必填

音色设计模型，固定值为 qwen-voice-design。

可选值：qwen-voice-design

示例:qwen-voice-design

object

必填

显示子属性

enum<string>

必填

操作类型，固定值为 list。

可选值：list

示例:list

integer

默认值0

页码，从 0 开始计数，取值范围：0–200。

示例:0

取值范围：0 <= x <= 200

integer

默认值10

每页返回的结果数量，必须大于 0。

示例:10

取值范围：x >= 1

响应

200-application/json

object

显示子属性

integer

当前页码。

示例:0

integer

每页条目数。

示例:10

integer

账号下的音色总数。

示例:26

object[]

音色对象数组。

显示子属性

string

音色名称。

示例:qwen-tts-vd-announcer-voice-20251210170454-a1b2

string

与该音色绑定的合成模型。

示例:qwen3-tts-vd-realtime-2026-01-15

string

语言代码。

示例:en

string

音色描述。

示例:A composed middle-aged male announcer with a deep, rich and magnetic voice.

string

创建音色时使用的试听文本。

示例:Dear listeners, hello everyone. Welcome to the evening news.

string

创建时间。

示例:2025-12-10 17:04:54

string

最后修改时间。

示例:2025-12-10 17:04:54

object

用量信息（查询操作时为空）。

string

请求 ID，可用于问题排查。

示例:xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx

cURL

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": "list",
    "page_size": 10,
    "page_index": 0
  }
}'

{
  "output": {
    "page_index": 0,
    "page_size": 10,
    "total_count": 26,
    "voice_list": [
      {
        "voice": "qwen-tts-vd-announcer-voice-20251210170454-a1b2",
        "target_model": "qwen3-tts-vd-realtime-2026-01-15",
        "language": "en",
        "voice_prompt": "A composed middle-aged male announcer with a deep, rich and magnetic voice.",
        "preview_text": "Dear listeners, hello everyone. Welcome to the evening news.",
        "gmt_create": "2025-12-10 17:04:54",
        "gmt_modified": "2025-12-10 17:04:54"
      }
    ]
  },
  "usage": {},
  "request_id": "xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}