# Stable Audio 2.5 · Audio to Audio

Edit and transform audio with Stable Audio 2.5 · Audio to Audio from fal through one Spiral API key. It runs in the background and returns audio. Pay as you go, with no subscription.

- Provider: fal
- Category: Audio
- Runs: In the background
- Returns: audio
- Released: 2025-09-10
- Tool id: `fal` / `fal-ai/stable-audio-25/audio-to-audio`
- Page: https://spiral.ai/tools/fal/fal-ai/stable-audio-25/audio-to-audio

## Pricing

$0.26 per run at the default inputs.

## Limits

- Longest queue wait: 1 hour
- Run deadline: 30 minutes
- Longest run, end to end: 255 minutes
- Largest inline input: 1 MB
- Largest input file: 2 GB
- Largest output: 5 GB

## Input

| Field | Kind | Allowed | Default | Description |
| --- | --- | --- | --- | --- |
| `prompt` (required) | text |  | — | The prompt to guide the audio generation |
| `audio_url` (required) | URL or file |  | — | The audio clip to transform |
| `strength` | number | 0.01 to 1 | 0.8 | Sometimes referred to as denoising, this parameter controls how much influence the `audio_url` parameter has on the generated audio. A value of 0 would yield audio that is identical to the input. A value of 1 would be as if you passed in no audio at all. |
| `num_inference_steps` | number (whole) | 4 to 8 | 8 | The number of steps to denoise the audio for |
| `total_seconds` | number (whole) | 1 to 190 | — | The duration of the audio clip to generate. If not provided, it will be set to the duration of the input audio. |
| `guidance_scale` | number | 1 to 25 | 1 | How strictly the diffusion process adheres to the prompt text (higher values make your audio closer to your prompt). |
| `seed` | number (whole) |  | — |  |

## Example

```bash
curl https://api.spiral.ai/v1/runs \
  -H "Authorization: Bearer $SPIRAL_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
    "provider": "fal",
    "model": "fal-ai/stable-audio-25/audio-to-audio",
    "input": {
      "prompt": "Post rock, guitars, bass, strings, euphoric, up-lifting, moody, flowing, raw, epic",
      "audio_url": "https://v3.fal.media/files/panda/1-0iezBUIePBa3Sz5YY5B_tmpy1jyshw9.wav"
    }
  }'
```

Try it in the Playground: https://spiral.ai/start?provider=fal&model=fal-ai%2Fstable-audio-25%2Faudio-to-audio

## Common questions

### Stable Audio 2.5 · Audio to Audio

**How much does Stable Audio 2.5 · Audio to Audio cost?**

$0.26 per run at the default inputs. You pay as you go from one Spiral balance, with no subscription, and a failed run is not charged.

**How do I use Stable Audio 2.5 · Audio to Audio through an API?**

Send `POST /v1/runs` with `"provider": "fal"`, `"model": "fal-ai/stable-audio-25/audio-to-audio"` and the input fields on this page, using one Spiral API key. It runs in the background: poll the run, or name a webhook to be told when it finishes.

**Do I need an account with fal to use Stable Audio 2.5 · Audio to Audio?**

No. Spiral runs it on its own fal account and charges your Spiral balance.

**Can my AI agent use Stable Audio 2.5 · Audio to Audio?**

Yes. Agents find and run it through Spiral's MCP server, CLI or agent skill, with the same API key.

