# Elevenlabs Music v2.5 API

> 更新的 v2.5 音乐创作版本，由文本提示词或基于分块的作曲方案驱动

根据最多 4100 个字符的 `prompt` 或 `composition_plan` 生成音乐。使用提示词时，`music_length_ms` 范围为 3000 到 600000 ms，`force_instrumental` 可确保不包含人声。`seed` 仅在搭配作曲方案时生效。`output_format` 提供多种 MP3 和 PCM 变体，默认值为 mp3_48000_192。

- Model id: `elevenlabs/music/v2.5`
- Made by: ElevenLabs
- Category: Text to Music
- Output: audio
- Price per minute of your output audio: $0.60 / minute of output audio (cheapest run $0.60 (600 API credits))
- Run: `POST https://api.doitong.ru/v1/run/elevenlabs/music/v2.5`
- Quote: `POST https://api.doitong.ru/v1/quote/elevenlabs/music/v2.5`
- Docs page: https://doitong.com/zh-CN/developers/models/elevenlabs/music/v2.5

## Pricing

Price: **$0.60 / minute of output audio**. Price per minute of your output audio: the input files are measured before the run (length, resolution, frame rate). The quote measures the same files and is exactly what the run charges.

The full example input below costs $1.20 = 1200 API credits (2 min output audio × $0.60).

Prices are the upstream price in USD, paid from the API balance in API credits (1000 API credits = 1 USD). `POST https://api.doitong.ru/v1/quote/elevenlabs/music/v2.5` with the same JSON body returns the exact price for that input; the quote is exactly what a run charges. Invalid input is never charged and failed or canceled requests are refunded automatically.

## Input parameters

| Parameter | Canonical name | Type | Required | Default | Allowed values / range | Description |
|---|---|---|---|---|---|---|
| `prompt` |  | string \| null | no |  | ≤ 4100 characters | 所需音乐的文本描述。 |
| `composition_plan` |  | object {chunks} \| null | no |  |  | 按片段组织的音乐创作计划。 |
| `composition_plan.chunks` |  | array of object {text, duration_ms, positive_styles, negative_styles, context_adherence, audio_reference} | yes |  | 1 – 30 items | 用于生成的有序片段，最多 30 个，总时长为 3000 ms 至 600000 ms。 |
| `composition_plan.chunks[].text` |  | string | yes |  |  | 片段生成文本，最多 30 行，每行最多 200 个字符。歌词可包含大括号中的行内指令，例如 {scratching}，也可在可选的开头部分名称（例如 [Verse 1]）之后出现。该部分名称必须包含 1–100 个字符。 |
| `composition_plan.chunks[].duration_ms` |  | integer | yes |  | 3,000 – 120,000 | 片段时长（单位为毫秒），范围为 3000 ms 至 120000 ms。 |
| `composition_plan.chunks[].positive_styles` |  | array of string | yes |  |  | 该片段所需的风格和音乐指示；第一片段的选择影响最大，因为它们决定歌曲的整体流派和基调。后续片段可以发展音乐、增加细节或改变方向；使用英文描述效果最佳。 |
| `composition_plan.chunks[].negative_styles` |  | array of string \| null | no |  |  | 该片段中要避免的音乐风格和指示；仅针对明确排除项提供条目，否则将列表留空是不错的默认选择。 |
| `composition_plan.chunks[].context_adherence` |  | enum (string) \| null | no |  | `low`, `medium`, `high` | 上下文遵循度在创作自由度与相邻片段的一致性之间进行平衡：选择 high 以保持一致，或选择 low 以允许更多创意偏离。 |
| `composition_plan.chunks[].audio_reference` |  | object {audio_url, start_ms, end_ms, strength} \| null | no |  |  | 该片段的风格条件音频片段；要塑造整首歌曲，请将其提供给第一片段。由于其参考内容会影响所有后续片段，此位置的影响最大。 |
| `music_length_ms` |  | integer \| null | no |  | 3,000 – 600,000 | 可选歌曲时长（单位为毫秒），范围为 3000 ms 至 600000 ms；仅在使用提示词时适用。省略时，模型根据提示词确定时长。 |
| `force_instrumental` |  | boolean | no | `false` |  | 仅器乐控制，仅在使用提示词时可用。设置为 true 可保证输出器乐；false 则根据提示词允许生成器乐或非器乐音乐。 |
| `seed` |  | integer \| null | no |  |  | 音乐生成初始化种子，仅可与 `composition_plan` 一起使用，用于提升参数和种子相同的多次运行之间的一致性。不保证结果完全复现。 |
| `output_format` |  | enum (string) | no | `mp3_48000_192` | `mp3_22050_32`, `mp3_24000_48`, `mp3_44100_32`, `mp3_44100_64`, `mp3_44100_96`, `mp3_44100_128`, `mp3_44100_192`, `mp3_48000_128`, `mp3_48000_192`, `mp3_48000_240`, `mp3_48000_320`, `pcm_8000`, `pcm_16000`, `pcm_22050`, `pcm_24000`, `pcm_32000`, `pcm_44100`, `pcm_48000`, `ulaw_8000`, `alaw_8000`, `opus_48000_32`, `opus_48000_64`, `opus_48000_96`, `opus_48000_128`, `opus_48000_192` | 使用 codec_sample_rate_bitrate 模式选择生成音频的格式。Twilio 音频输入通常使用 μ-law，也写作 mu-law 或近似写作 u-law；MP3 示例为 mp3_22050_32，表示采样率为 22.05 kHz、比特率为 32 kbs。 |

## Example input

Required parameters only:

```json
{}
```

A fuller example:

```json
{
  "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
}
```

## Run it

Set `DOITONG_API_KEY` to a key from https://doitong.com/developers/dashboard#keys. `?wait=20` returns the finished request in the same call when it is ready within 20 seconds; otherwise poll `GET /requests/{id}` (it also accepts `?wait=`), or pass `webhook_url`.

### curl

```bash
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://api.doitong.ru/v1/run/elevenlabs/music/v2.5?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
  }'

# Still "queued" or "running"? Poll with the id from the response:
curl "https://api.doitong.ru/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"
```

### JavaScript

```javascript
const API = "https://api.doitong.ru/v1";
const headers = {
  "Authorization": "Bearer " + process.env.DOITONG_API_KEY,
  "Content-Type": "application/json",
};

// Run the model; wait up to 20 s for the finished result in the same call
let res = await fetch(API + "/run/elevenlabs/music/v2.5?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
  }),
});
let request = await res.json();
if (!res.ok) throw new Error(request.error.code + ": " + request.error.message);

// Not finished yet: long-poll until it is
while (request.status === "queued" || request.status === "running") {
  res = await fetch(API + "/requests/" + request.id + "?wait=20", { headers });
  request = await res.json();
}
if (request.status !== "succeeded") throw new Error(JSON.stringify(request.error));
console.log(request.outputs.map((o) => o.url), request.cost.credits + " API credits ($" + request.cost.usd + ")");
```

### Python

```python
import os
import requests

API = "https://api.doitong.ru/v1"
headers = {"Authorization": "Bearer " + os.environ["DOITONG_API_KEY"]}

payload = {
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
}

# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/elevenlabs/music/v2.5", params={"wait": 20}, json=payload, headers=headers)
request = r.json()
if not r.ok:
    raise RuntimeError(request["error"]["code"] + ": " + request["error"]["message"])

# Not finished yet: long-poll until it is
while request["status"] in ("queued", "running"):
    request = requests.get(API + "/requests/" + request["id"], params={"wait": 20}, headers=headers).json()
if request["status"] != "succeeded":
    raise RuntimeError(request["error"])
print([o["url"] for o in request["outputs"]], request["cost"]["credits"], "API credits", "$" + request["cost"]["usd"])
```

### MCP

The MCP server at `https://api.doitong.ru/v1/mcp` exposes the tools `search_models`, `get_model`, `quote`, `run`, `get_request`, `cancel_request`, `list_requests`, `create_upload` and `get_account`. A `run` call for this model:

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "run",
    "arguments": {
      "model_id": "elevenlabs/music/v2.5",
      "input": {
        "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
      },
      "wait_seconds": 20
    }
  }
}
```

## Response

Every call returns a request object. `status` is one of `queued`, `running`, `succeeded`, `failed`, `canceled`. `outputs` lists the generated files with URLs on our storage (kept forever, or 7 days with `?storage=temporary`; `storage` says which); `output` is the model's own result object with the same URLs.

```json
{
  "id": "req_8k2m4q7x1z9c3v5b6n0p2r4t",
  "object": "request",
  "model": "elevenlabs/music/v2.5",
  "status": "succeeded",
  "created_at": "2026-10-20T12:00:00Z",
  "started_at": "2026-10-20T12:00:02Z",
  "completed_at": "2026-10-20T12:00:09Z",
  "queue_position": null,
  "cost": {
    "credits": 1200,
    "usd": "1.20",
    "charged": 1200,
    "refunded": 0
  },
  "input": {
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
  },
  "output": {
    "audio": {
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.mp3",
      "content_type": "audio/mpeg",
      "file_name": "0-output.mp3",
      "file_size": 1843200
    }
  },
  "outputs": [
    {
      "type": "audio",
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.mp3",
      "content_type": "audio/mpeg",
      "file_size": 1843200,
      "duration": 12,
      "stored": true
    }
  ],
  "error": null,
  "metrics": {
    "inference_seconds": 6.8
  },
  "urls": {
    "self": "https://api.doitong.ru/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
    "cancel": "https://api.doitong.ru/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t/cancel"
  }
}
```

### Output fields (`output`)

| Field | Type | Description |
|---|---|---|
| `audio` | object {url, content_type, file_name, file_size} | 编码为 MP3 音频的生成音乐文件。 |

## Related models

- [Elevenlabs Music v2](https://doitong.com/developers/models/elevenlabs/music/v2.md) (`elevenlabs/music/v2`): $0.60 / minute of output audio
- [MiniMax Music 3](https://doitong.com/developers/models/minimax/music-3.md) (`minimax/music-3`): $0.002 / second
- [Elevenlabs Music](https://doitong.com/developers/models/elevenlabs/music.md) (`elevenlabs/music`): $0.60 / minute of output audio
- [ACE Step](https://doitong.com/developers/models/ace-step.md) (`ace-step`): $0.0002 / second
- [ACE Step Audio Inpaint](https://doitong.com/developers/models/ace-step/audio-inpaint.md) (`ace-step/audio-inpaint`): $0.0002 / second of input audio
- [ACE Step Audio Outpaint](https://doitong.com/developers/models/ace-step/audio-outpaint.md) (`ace-step/audio-outpaint`): $0.0002 / second of output audio
- [ACE Step Audio To Audio](https://doitong.com/developers/models/ace-step/audio-to-audio.md) (`ace-step/audio-to-audio`): $0.0002 / second of input audio
- [ACE Step Prompt To Audio](https://doitong.com/developers/models/ace-step/prompt-to-audio.md) (`ace-step/prompt-to-audio`): $0.0002 / second

## Links

- HTML page: https://doitong.com/developers/models/elevenlabs/music/v2.5
- All models and guides for AI agents: https://doitong.com/developers/llms.txt
- OpenAPI 3.1 with this model's typed request body: https://doitong.com/developers/openapi.json?model=elevenlabs/music/v2.5
- Errors: https://doitong.com/developers/docs/errors
- Model details as JSON: https://api.doitong.ru/v1/models/elevenlabs/music/v2.5