# Stable Audio 2.5

> Stability AI's Stable Audio 2.5. Generates high-quality music and sound up to 190 seconds from a text prompt, with step count and CFG scale controls. Returns an MP3 file.

- **Provider**: replicate
- **Model ID**: stability-ai/stable-audio-2.5
- **Category**: music_generation
- **Credits**: 470 per request
- **Pricing Type**: fixed

## API Endpoint

Base URL: https://api.core.today/v1

### Create Prediction
POST /predictions

### Get Status
GET /predictions/{job_id}

### Cancel
DELETE /predictions/{job_id}

## Authentication

Header: `X-API-Key: YOUR_API_KEY`

## Input Parameters

- `prompt` (string, **required**): Text prompt describing the desired audio (genre, mood, instruments, tempo, structure).
- `duration` (integer, optional): Duration of generated audio in seconds (1-190). Price is flat, so longer clips cost the same. (Default: `190`; Range: min: 1, max: 190)
- `seed` (integer, optional): Random seed for reproducible results. Leave blank for a random seed.
- `steps` (integer, optional): Number of diffusion steps (4-8). Higher is better quality but slower. (Default: `8`; Range: min: 4, max: 8)
- `cfg_scale` (number, optional): Classifier-free guidance scale (1-25). Higher means more prompt adherence. (Default: `1`; Range: min: 1, max: 25)

## Example Request

```json
{
  "model": "stability-ai/stable-audio-2.5",
  "input": {
    "duration": 90,
    "prompt": "Pop, Pop-Electronic, Ballad, Drum Machine, Bass, Lush Synthesizer Pads, Synth Bass, Vocal Sample Chops, Melancholic, Atmospheric, well-arranged composition, 115 BPM",
    "steps": 8,
    "cfg_scale": 1
  }
}
```

## Response Format

```json
{
  "job_id": "abc123",
  "status": "pending",
  "provider": "replicate",
  "model": "stability-ai/stable-audio-2.5",
  "created_at": "2026-01-01T00:00:00Z",
  "result": null,
  "error": null,
  "credits_used": null
}
```

Status values: `pending`, `processing`, `completed`, `failed`, `cancelled`

When the job is `completed`, `result` holds the output URL(s) or data and `credits_used` the net credits charged. When it is `failed`, `error` and `error_code` say why and the charge is refunded.

## Usage Flow

1. POST /predictions with model and input → receive job_id
2. Poll GET /predictions/{job_id} until status is `completed` or `failed`
3. Result contains output URL(s) or data

## Pricing

- 470 credits per request

These are list prices. The amount charged is rounded, and large charges are discounted progressively. `POST /predictions/estimate` with the same `model` and `input` returns the charge for that input without creating a job (an estimate when the price depends on the output).

## Output Type

url

## Tags

music-generation, text-to-music, sound-design, instrumental, stability-ai

## Documentation

https://replicate.com/stability-ai/stable-audio-2.5