# ElevenLabs Music v2.5 Text-to-Music — Atlas Cloud API

> Generate studio-quality songs or instrumentals from a text prompt, from 3 seconds up to 10 minutes, in any genre and many languages.

This is the machine-readable API reference for **ElevenLabs Music v2.5 Text-to-Music** on Atlas Cloud,
a unified API platform with a catalog of 600+ models across text, image, video, audio and 3D.

- **Model ID**: `elevenlabs/music-v2.5/text-to-music`
- **Built by**: ELEVENLABS
- **Modality**: Audio
- **Model page**: https://www.atlascloud.ai/models/elevenlabs/music-v2.5/text-to-music
- **API key**: https://www.atlascloud.ai/console/api-keys
- **Docs**: https://www.atlascloud.ai/docs

## Pricing on Atlas Cloud

- $0.178 per minute of audio
- Pay-as-you-go. No minimum spend, no subscription required.

> **These are the authoritative Atlas Cloud rates for this model.** Any price that
> appears in the vendor description further down refers to a different platform or
> a different model variant and does not apply here.

## Use this model from an AI agent

Atlas Cloud ships three first-party integration surfaces. All three authenticate
with the same API key via the `ATLASCLOUD_API_KEY` environment variable.

### MCP server

The official MCP server (`atlascloud-mcp`) exposes this model to any
MCP-compatible host — Claude Code, OpenAI Codex, Cursor, Gemini CLI, Goose,
Claude Desktop. One-line install:

```bash
# Claude Code
claude mcp add atlascloud -- npx -y atlascloud-mcp

# OpenAI Codex CLI
codex mcp add atlascloud -- npx -y atlascloud-mcp

# Gemini CLI
gemini mcp add atlascloud -- npx -y atlascloud-mcp

export ATLASCLOUD_API_KEY="your-api-key"
```

Then ask in plain English; the agent calls `atlas_generate_audio` with `model: "elevenlabs/music-v2.5/text-to-music"`.
The server fetches each model's schema and validates parameters before submitting,
so invalid requests fail fast without spending credits.

MCP docs: https://www.atlascloud.ai/docs/mcp-server

### Agent Skills

`atlas-cloud-skills` is a portable skill package (API reference, code templates in
Python / Node.js / cURL, model IDs with pricing) for Claude Code, Cursor, Codex and
12+ other agents:

```bash
npx skills add AtlasCloudAI/atlas-cloud-skills
export ATLASCLOUD_API_KEY="your-api-key"
```

Skills docs: https://www.atlascloud.ai/docs/skills

### CLI

The `atlas` binary runs Atlas Cloud from a terminal or CI script. Async media jobs
are polled and downloaded automatically (use `--no-download` when a script only
needs the output URLs):

```bash
# Install (Homebrew, npm, or shell installer)
brew install AtlasCloudAI/tap/atlascloud
# npm install -g atlascloud-cli
# curl -fsSL https://raw.githubusercontent.com/AtlasCloudAI/cli/main/install.sh | sh

atlas auth login
atlas models get elevenlabs/music-v2.5/text-to-music --json
```

CLI docs: https://www.atlascloud.ai/docs/cli

## HTTP API reference

- **Submit endpoint (POST)**: `https://api.atlascloud.ai/api/v1/model/generateAudio` — start an async generation; returns a `prediction_id`
- **Poll endpoint (GET)**: `https://api.atlascloud.ai/api/v1/model/prediction/{prediction_id}` — poll this until the prediction finishes
- **Model ID**: `elevenlabs/music-v2.5/text-to-music`


## API Information

This model can be used via our HTTP API or more conveniently via our client libraries.
See the input and output schema below, as well as the usage examples.


### Input Schema

The API accepts the following input parameters:

- **`model`** (`string`, _required_):
  Model name.
  - Default: `"elevenlabs/music-v2.5/text-to-music"`

- **`prompt`** (`string`, _optional_):
  Describe the music: genre, mood, instruments, tempo, vocals and lyrics, e.g. "Upbeat lo-fi hip hop with mellow piano and soft drums". Up to 2,000 characters. Required unless composition_plan is sent; the two cannot be combined.
  - Default: `"Upbeat lo-fi hip hop instrumental with mellow piano, vinyl crackle and soft drums"`

- **`duration`** (`integer`, _optional_):
  Length of the music in seconds, 3–600 (up to 10 minutes). Billed per requested second. With composition_plan it is required and must equal the plan's total duration_ms rounded up to whole seconds.
  - Default: `30`
  - Min: 3
  - Max: 600

- **`force_instrumental`** (`boolean`, _optional_):
  Generate instrumental music only, with no vocals. Prompt only; not allowed with composition_plan.
  - Default: `false`

- **`composition_plan`** (`object`, _optional_):
  Section-by-section plan, used instead of prompt. Up to 30 chunks, each 3,000–120,000 ms, 3–600 s in total. The first chunk's styles have the most influence on the whole track. The composition_plan in a Detailed model's metadata file can be sent back as is.
  - Properties:
    - **`chunks`** (`array[object]`, _required_):
      - Min items: 1
      - Max items: 30
      - Item properties:
        - **`text`** (`string`, _required_):
          Optional [Section name] on the first line, then lyrics and {directions}. At most 30 lines of up to 200 characters.

        - **`duration_ms`** (`integer`, _required_):
          Length of this chunk in milliseconds.
          - Min: 3000
          - Max: 120000

        - **`positive_styles`** (`array[string]`, _required_):
          Styles to include, e.g. ["synthwave", "analog drum machine"].
          - Min items: 1

        - **`negative_styles`** (`array[string]`, _optional_):
          Styles to avoid.

        - **`context_adherence`** (`string`, _optional_):
          How closely this chunk follows the preceding music. Default high.
          - Options: "low", "medium", "high"





**Required Parameters Example**:

```json
{
  "model": "elevenlabs/music-v2.5/text-to-music"
}
```


**Full Example**:

```json
{
  "model": "elevenlabs/music-v2.5/text-to-music",
  "prompt": "Upbeat lo-fi hip hop instrumental with mellow piano, vinyl crackle and soft drums",
  "duration": 30,
  "force_instrumental": false,
  "composition_plan": {
    "chunks": [
      {
        "text": "",
        "duration_ms": 3000,
        "positive_styles": [
          ""
        ],
        "negative_styles": [
          ""
        ],
        "context_adherence": "low"
      }
    ]
  }
}
```


### Output Schema

The API returns the following output format:


- **`id`** (`string`, _optional_):
  Unique identifier for the prediction.

- **`model`** (`string`, _optional_):
  Model ID used for the prediction.

- **`status`** (`string`, _optional_):
  Status of the task: created, processing, completed, or failed.

- **`outputs`** (`array[string]`, _optional_):
  Array with the URL of the generated MP3 (48 kHz, 192 kbps).

- **`created_at`** (`string`, _optional_):
  ISO timestamp of when the request was created.

- **`urls`** (`object`, _optional_):
  Object containing related API endpoints.



**Example Response**:

```json
{
  "id": "",
  "model": "",
  "status": "",
  "outputs": [
    ""
  ],
  "created_at": "",
  "urls": {}
}
```


## Usage Examples

### cURL

```bash
# Step 1: Start generation (async)
curl -X POST "https://api.atlascloud.ai/api/v1/model/generateAudio" \
  -H "Authorization: Bearer $ATLASCLOUD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "elevenlabs/music-v2.5/text-to-music",
  "prompt": "Upbeat lo-fi hip hop instrumental with mellow piano, vinyl crackle and soft drums",
  "duration": 30,
  "force_instrumental": false,
  "composition_plan": {
    "chunks": [
      {
        "text": "",
        "duration_ms": 3000,
        "positive_styles": [
          ""
        ],
        "negative_styles": [
          ""
        ],
        "context_adherence": "low"
      }
    ]
  }
}'

# Response will contain: {"code": 200, "data": {"id": "prediction_id", "status": "processing"}}

# Step 2: Poll for result (replace {prediction_id} with the id returned above)
curl -X GET "https://api.atlascloud.ai/api/v1/model/prediction/{prediction_id}" \
  -H "Authorization: Bearer $ATLASCLOUD_API_KEY"

# Keep polling until status is "completed", "succeeded" or "failed"
# When completed, outputs will contain the generated content URL(s)
```

## Additional Resources

### Documentation

- [Model Playground](https://www.atlascloud.ai/models/elevenlabs/music-v2.5/text-to-music)

## About this model

_Vendor-supplied description. Any pricing or endpoint mentioned below refers to_
_other platforms — use the Atlas Cloud values above._

### ElevenLabs Music v2.5 Text-to-Music

**ElevenLabs Music v2.5** turns a text prompt into a studio-quality track: full songs with vocals and lyrics, or instrumentals, in almost any genre and in many languages. Tracks can be anywhere from 3 seconds to 10 minutes long.

#### Why Choose This?

- **Describe it, hear it.** Name the genre, mood, instruments, tempo and vocals, or write the lyrics into the prompt.
- **3 seconds to 10 minutes.** Short stingers and jingles up to full-length songs, at the exact length you ask for.
- **Instrumental on demand.** Turn on `force_instrumental` for background music with no vocals.
- **Many languages.** Vocals in English, Spanish, German, Japanese and more.
- **Ready to use.** MP3 at 48 kHz, 192 kbps.

#### Parameters

| Parameter | Required | Description |
| --- | --- | --- |
| model | Yes | `elevenlabs/music-v2.5/text-to-music` |
| prompt | Yes, unless `composition_plan` is sent | Description of the music, up to 2,000 characters. Cannot be combined with `composition_plan`. |
| duration | No (required with `composition_plan`) | Length in seconds, integer 3–600. Default `30`. With `composition_plan` it must equal the plan's total `duration_ms`, rounded up to whole seconds. |
| force_instrumental | No | `true` for instrumental music with no vocals. Default `false`. Prompt only. |
| composition_plan | No | Section-by-section plan used instead of `prompt`. See [Composition Plan](#composition-plan). |
| seed | No | Integer 0–2147483647 for reproducible results. Only with `composition_plan`. |

#### Pricing

Billed per second of requested `duration` (with a composition plan, the plan's total length): **$0.003125 per second** ($0.1875 per minute). The default 30 seconds costs $0.09375; 10 minutes costs $1.875.

#### How to Use

_(Description truncated. Full text on the model page.)_

---

Atlas Cloud — one API for multimodal AI. Model page: https://www.atlascloud.ai/models/elevenlabs/music-v2.5/text-to-music · Docs: https://www.atlascloud.ai/docs
