验证并创建 Voice

curl --request POST \
  --url https://apistable.ai/api/v1/tasks/create_task \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "suno_voice_create",
  "input": {
    "voice_upload_task_id": "YOUR_UPLOAD_TASK_ID",
    "phrase_id": "YOUR_PHRASE_ID",
    "upload_url": "https://example.com/verification.wav"
  }
}
'

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    model: 'suno_voice_create',
    input: {
      voice_upload_task_id: 'YOUR_UPLOAD_TASK_ID',
      phrase_id: 'YOUR_PHRASE_ID',
      upload_url: 'https://example.com/verification.wav'
    }
  })
};

fetch('https://apistable.ai/api/v1/tasks/create_task', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

import requests

url = "https://apistable.ai/api/v1/tasks/create_task"

payload = {
    "model": "suno_voice_create",
    "input": {
        "voice_upload_task_id": "YOUR_UPLOAD_TASK_ID",
        "phrase_id": "YOUR_PHRASE_ID",
        "upload_url": "https://example.com/verification.wav"
    }
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

{
  "code": 200,
  "msg": "success",
  "data": {
    "task_id": "<string>"
  }
}

{
  "code": 123,
  "msg": "<string>",
  "data": null
}

{
  "code": 123,
  "msg": "<string>",
  "data": null
}

{
  "code": 123,
  "msg": "<string>",
  "data": null
}

{
  "code": 123,
  "msg": "<string>",
  "data": null
}

{
  "code": 123,
  "msg": "<string>",
  "data": null
}

{
  "code": 123,
  "msg": "<string>",
  "data": null
}

{
  "code": 123,
  "msg": "<string>",
  "data": null
}

{
  "code": 123,
  "msg": "<string>",
  "data": null
}

{
  "code": 123,
  "msg": "<string>",
  "data": null
}

{
  "code": 123,
  "msg": "<string>",
  "data": null
}

POST

api

tasks

create_task

验证并创建 Voice

curl --request POST \
  --url https://apistable.ai/api/v1/tasks/create_task \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "suno_voice_create",
  "input": {
    "voice_upload_task_id": "YOUR_UPLOAD_TASK_ID",
    "phrase_id": "YOUR_PHRASE_ID",
    "upload_url": "https://example.com/verification.wav"
  }
}
'

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    model: 'suno_voice_create',
    input: {
      voice_upload_task_id: 'YOUR_UPLOAD_TASK_ID',
      phrase_id: 'YOUR_PHRASE_ID',
      upload_url: 'https://example.com/verification.wav'
    }
  })
};

fetch('https://apistable.ai/api/v1/tasks/create_task', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

import requests

url = "https://apistable.ai/api/v1/tasks/create_task"

payload = {
    "model": "suno_voice_create",
    "input": {
        "voice_upload_task_id": "YOUR_UPLOAD_TASK_ID",
        "phrase_id": "YOUR_PHRASE_ID",
        "upload_url": "https://example.com/verification.wav"
    }
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

{
  "code": 200,
  "msg": "success",
  "data": {
    "task_id": "<string>"
  }
}

{
  "code": 123,
  "msg": "<string>",
  "data": null
}

{
  "code": 123,
  "msg": "<string>",
  "data": null
}

{
  "code": 123,
  "msg": "<string>",
  "data": null
}

{
  "code": 123,
  "msg": "<string>",
  "data": null
}

{
  "code": 123,
  "msg": "<string>",
  "data": null
}

{
  "code": 123,
  "msg": "<string>",
  "data": null
}

{
  "code": 123,
  "msg": "<string>",
  "data": null
}

{
  "code": 123,
  "msg": "<string>",
  "data": null
}

{
  "code": 123,
  "msg": "<string>",
  "data": null
}

{
  "code": 123,
  "msg": "<string>",
  "data": null
}

能力按服务端配置逐项启用。未启用操作返回 503 且不创建任务；音乐积分扣除当前未启用。

调用步骤

使用同一次样本上传得到的任务 ID 和短句 ID，提交本人朗读该短句的录音 URL。

1. 按下方示例准备输入，将占位地址和 ID 换成你有权使用的资源。
1. 将 model 设为 suno_voice_create，参数放在 input 内。提交一次并保存返回的 task_id。
1. 查询已保存的任务，或接收回调。任务仍在处理中时继续等待，不重新提交同一操作。
保存 result.voice_id，复用前可通过 GET /api/v1/voices/{voice_id} 检查可用性。

创建任务

将model和input发送到统一任务入口；可在顶层传公开HTTPS callback_url。资源ID均为本账户的本站ID。当前音乐积分扣除未启用。

{
  "model": "suno_voice_create",
  "input": {
    "voice_upload_task_id": "YOUR_UPLOAD_TASK_ID",
    "phrase_id": "YOUR_PHRASE_ID",
    "upload_url": "https://example.com/verification.wav"
  }
}

受理响应

HTTP 200仅表示受理。查询GET /api/v1/tasks/{task_id}，直到data.status为succeeded或failed。成功后读取data.result；失败原因位于data.message。

{
  "code": 200,
  "msg": "success",
  "data": {
    "task_id": "YOUR_TASK_ID"
  }
}

参数速查

字段	类型	必填	说明与限制
voice_upload_task_id	string	是	suno_voice_upload 返回的本站任务 ID，绑定同一账户。 maxLength: 200
phrase_id	string	是	本站验证短句 ID，须绑定所选声音上传任务。 maxLength: 200
upload_url	string	是	公开HTTPS音频URL，端口443且不含用户名密码。接受包含可读音轨的MP3/WAV/FLAC/OGG/M4A/AAC，大小限制见具体操作。
name	string	否 / 依条件	Voice 或 Persona 展示名称。 maxLength: 100
description	string	否 / 依条件	Voice 或 Persona 描述。 maxLength: 1000

输入与限制

下方Schema列出支持字段、类型和基础限制；还须遵守“重要条件”，跨字段与来源资源校验不完全体现在JSON Schema中。未知参数会被拒绝。URL 参数仅接受公开 HTTPS 地址，不接受文件对象。

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "type": "object",
  "properties": {
    "voice_upload_task_id": {
      "type": "string",
      "minLength": 1,
      "maxLength": 200,
      "description": "suno_voice_upload 返回的本站任务 ID，绑定同一账户。"
    },
    "phrase_id": {
      "type": "string",
      "minLength": 1,
      "maxLength": 200,
      "description": "本站验证短句 ID，须绑定所选声音上传任务。"
    },
    "upload_url": {
      "type": "string",
      "format": "uri",
      "description": "公开HTTPS音频URL，端口443且不含用户名密码。接受包含可读音轨的MP3/WAV/FLAC/OGG/M4A/AAC，大小限制见具体操作。"
    },
    "name": {
      "type": "string",
      "maxLength": 100,
      "description": "Voice 或 Persona 展示名称。"
    },
    "description": {
      "type": "string",
      "maxLength": 1000,
      "description": "Voice 或 Persona 描述。"
    }
  },
  "required": [
    "voice_upload_task_id",
    "phrase_id",
    "upload_url"
  ],
  "additionalProperties": false
}

重要条件

样本会话须已准备完成且未过期；phrase_id必须属于同一voice_upload_task_id。upload_url为本人朗读返回短句的新录音。24小时样本会话到期后须从suno_voice_upload重新开始。
音频URL必须包含可读且时长大于零的MP3/WAV/FLAC/OGG/M4A/AAC音轨，每个文件最多500 MiB。URL须为可公开读取的HTTPS地址、端口443，不含用户名密码或私网地址，且应持续可访问直到任务结束。
上传文件保留24小时，生成文件保留14天，任务详情保留30天；复用文件沿用原到期时间。有效Voice/Persona身份映射与任务日志清理分开处理，请及时下载需长期保存的文件。

结果 Schema

创建响应为 {code:200,msg:“success”,data:{task_id}}，轮询 GET /api/v1/tasks/{task_id}。成功时 data.result 为符合下方 Schema 的对象，其他状态为 null；input 仍为 JSON 字符串。

{
  "type": "object",
  "required": [
    "voice_id",
    "name",
    "description",
    "available"
  ],
  "properties": {
    "voice_id": {
      "type": "string"
    },
    "name": {
      "type": "string"
    },
    "description": {
      "type": "string"
    },
    "available": {
      "type": "boolean"
    }
  },
  "additionalProperties": false
}

开始使用 APIstable（必读）

模型市场

验证并创建 Voice

调用步骤

创建任务

受理响应

参数速查

输入与限制

重要条件

结果 Schema

相关流程

授权

请求体

响应

​调用步骤

​创建任务

​受理响应

​参数速查

​输入与限制

​重要条件

​结果 Schema

​相关流程

授权

请求体

响应

调用步骤

创建任务

受理响应

参数速查

输入与限制

重要条件

结果 Schema

相关流程