> ## Documentation Index
> Fetch the complete documentation index at: https://docs.oxen.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Eleven Music v2.5: Composition Plan

> Section-by-section songs with set lyrics and timing

> [card] [Try Eleven Music v2.5: Composition Plan in the Workbench](https://www.oxen.ai/ai/workbench?model=elevenlabs-music-v2-5-composition)
>
> Run this model interactively, tune parameters, and compare outputs.

**Model ID:** `elevenlabs-music-v2-5-composition`

Eleven Music v2.5 with a composition plan builds a song section by section, with its own styles, length, and lyrics for each part.

Set the styles the whole song should have and avoid, then lay out sections such as intro, verse, chorus, and bridge, each with its own direction, duration, and lyric lines. Compared with a single prompt this gives exact control over structure and timing, which suits scoring to picture, songs with set lyrics, and tracks that have to hit a length. The track runs as long as its sections add up to, up to 10 minutes.

| Metric | Value |
| - | - |
| Max Output | 10 minutes, up to 30 sections |
| Multilingual | Yes (lyrics in many languages) |

## Example request

> [!TIP]
>
> Use the [Workbench](https://www.oxen.ai/ai/workbench?model=elevenlabs-music-v2-5-composition) as a request builder: configure parameters for this model in the UI, then open the **API** tab to copy the exact cURL or Python call.

```bash cURL theme={null}
curl -X POST https://hub.oxen.ai/api/ai/audio/speech \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OXEN_API_KEY" \
  -d '{
  "model": "elevenlabs-music-v2-5-composition",
  "styles": "<styles>",
  "sections": [
    {}
  ],
  "input": "Welcome to Oxen"
}'
```

```python Python theme={null}
import os
import requests

response = requests.post(
    "https://hub.oxen.ai/api/ai/audio/speech",
    headers={
        "Content-Type": "application/json",
        "Authorization": f"Bearer {os.environ['OXEN_API_KEY']}",
    },
    json={
        "model": "elevenlabs-music-v2-5-composition",
        "styles": "<styles>",
        "sections": [
            {}
        ],
        "input": "Welcome to Oxen"
    },
)
response.raise_for_status()
print(response.json())
```

## Fetch model details

The [models endpoint](https://docs.oxen.ai/inference-api/reference/models/overview.md) returns the full model object, including its `json_request_schema`.

```bash theme={null}
curl -H "Authorization: Bearer $OXEN_API_KEY" https://hub.oxen.ai/api/ai/models/elevenlabs-music-v2-5-composition
```

## Request parameters

### Required parameters

| Field | Type | Default | Description |
| - | - | - | - |
| `styles` | `string` | — | Styles and directions for the whole song, separated by commas, e.g. warm indie folk, fingerpicked acoustic guitar, 92 BPM. |
| `sections` | `array<object>` | — | The song's sections in order. Up to 30; they add up to the song's length. |

### Optional parameters

| Field | Type | Default | Description |
| - | - | - | - |
| `exclude_styles` | `string` | — | Styles the song should avoid, separated by commas. |
| `seed` | `integer` | — | Optional seed. The same seed and plan give more consistent results, though not identical ones. Range: 0 – 2147483647. |


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.