# Stable Audio 2.5 - Core.Today AI API

> 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. Flat price per generation regardless of length. Returns an MP3 file.

- **Provider**: Stability AI
- **Model ID**: stability-ai/stable-audio-2.5
- **Category**: Audio & TTS
- **Credits**: 470 per generation (any length up to 190s)
- **Speed**: Medium
- **Quality**: High

## Features
- Up to 190 seconds per generation at a flat price
- Music and sound design from one model
- Diffusion steps (4-8) and CFG scale controls
- Seed for reproducible results

## Use Cases
- Long background tracks and ambient beds
- Sound design and textures for video
- Instrumental loops and stems

## API Endpoint

Base URL: https://api.core.today/v1
Create Prediction: POST /predictions
Get Status: GET /predictions/{job_id}

## Authentication
Header: X-API-Key: YOUR_API_KEY

## Input Parameters

### Required
- **prompt**: string - Text prompt describing the desired audio (genre, mood, instruments, tempo, structure)

### Optional
- **duration**: integer (default: 190) - Duration in seconds (1-190). Price is flat, so longer clips cost the same
- **steps**: integer (default: 8) - Number of diffusion steps (4-8). Higher is better quality but slower
- **cfg_scale**: number (default: 1) - Classifier-free guidance scale (1-25). Higher means more prompt adherence
- **seed**: integer - Random seed for reproducible results. Leave blank for random

## Examples

### Core.Today theme (instrumental)
The same company-theme prompt given to every instrumental model — compare the results side by side
```json
{
  "model": "stability-ai/stable-audio-2.5",
  "input": {
    "prompt": "Upbeat K-pop electro-pop company jingle instrumental, 128 BPM, synth brass stabs, punchy drums, bright synth lead, catchy hook, fun and playful, radio-ready mix",
    "duration": 60,
    "steps": 8,
    "cfg_scale": 1
  }
}
```

### Electronic pop ballad
Tag-style prompt listing genre, instruments and mood
```json
{
  "model": "stability-ai/stable-audio-2.5",
  "input": {
    "prompt": "Pop, Pop-Electronic, Ballad, Drum Machine, Bass, Lush Synthesizer Pads, Synth Bass, Vocal Sample Chops, Melancholic, Atmospheric, well-arranged composition, 115 BPM",
    "duration": 60,
    "steps": 8,
    "cfg_scale": 1
  }
}
```

## Response Format
```json
{
  "job_id": "abc123",
  "status": "pending | processing | completed | failed",
  "result": "URL or data (when completed)"
}
```

## Usage Flow
1. POST /predictions with model and input -> receive job_id
2. GET /predictions/{job_id} -> poll until status is completed or failed
3. Result contains output URL(s)

## Tips
- Write prompts as comma-separated descriptors: genre, instruments, mood, BPM
- Price does not depend on duration — ask for the full length you need
- Keep steps at 8 for final output; 4 is faster for drafts
- cfg_scale 1 is the balanced default; raise it only when the prompt is ignored