# Stable Audio 3 Small SFX MCP and API by Stability AI | FlyMy.AI

> Stable Audio 3 Small SFX makes sound effects of up to 2 minutes from a text description: impacts, foley and ambience.

Page: https://flymy.ai/mcp/models/stable-audio-3-small-sfx-text-to-audio/

MCP / Models / Voice, music and sound

# Stable Audio 3 Small SFX MCP: sound effects up to 2 minutes

Stable Audio 3 Small SFX makes sound effects of up to 2 minutes from a text description: impacts, foley and ambience. Run it from Claude Code, Codex, Cursor or any MCP client through one FlyMy.AI MCP, or call its API.

[Use Stable Audio 3 Small SFX](https://flymy.ai/mcp/models/stable-audio-3-small-sfx-text-to-audio/#start) [Inputs and price](https://flymy.ai/mcp/models/stable-audio-3-small-sfx-text-to-audio/#inputs)

No API key, $0.0206 / run, Sound effects, Stability AI, Commercial use

$ YOUR NEXT RUN

Claude Code, Codex, Cursor, Any agent

## Use Stable Audio 3 Small SFX in your assistant

Paste this prompt into Claude Code, Codex, Cursor or any agent. It reads the guide and helps you connect.

```
Read https://flymy.ai/skill.md and https://flymy.ai/mcp/models/stable-audio-3-small-sfx-text-to-audio.md. Help me connect the FlyMy.AI MCP to this assistant, then run Stable Audio 3 Small SFX (flymyai/stable-audio-3-small-sfx-text-to-audio) for this task: Make 20 seconds of rain on a metal roof with Stable Audio 3 Small SFX.
```

[Open FlyMy.AI](https://app.flymy.ai/new-agent) [Download brief](https://flymy.ai/mcp/models/stable-audio-3-small-sfx-text-to-audio.md)

## What Stable Audio 3 Small SFX does

Say what the sound is in prompt, required: what makes it, how and where, for example heavy rain on a metal roof; negative_prompt names what to keep out, such as music or voices. duration is 1 to 120 seconds (30 by default). seed repeats a result and num_inference_steps (1 to 100, 8 by default) rarely needs changing on this distilled model; output_format is mp3 (the default, 192 kbit/s), wav, flac, ogg, opus, m4a or aac. Outputs: audio, the sound, and seed. It is a 459-million-parameter text-to-sound-effects model from Stability AI, designed to run on a phone or a laptop: an impact, footsteps, a door, weather, a crowd or an ambience bed.

It is billed at one flat price per audio, whatever the length. It makes one sound per request. It makes neither music with lyrics nor speech, and it does not add sound to a video (Mirelo SFX 2.0 Video to Audio does).

## Stable Audio 3 Small SFX inputs

Every input of `flymyai/stable-audio-3-small-sfx-text-to-audio` as its live schema lists them. Returns `audio` (array), `seed` (string).

| Input | Type, values and default |
|---|---|
| [#](https://flymy.ai/mcp/models/stable-audio-3-small-sfx-text-to-audio/#input-prompt) `prompt` | string required Describe the sound: what makes it, how and where, e.g. heavy rain on a metal roof |
| [#](https://flymy.ai/mcp/models/stable-audio-3-small-sfx-text-to-audio/#input-negative_prompt) `negative_prompt` | string optional Qualities to keep out of the sound, e.g. music or voices |
| [#](https://flymy.ai/mcp/models/stable-audio-3-small-sfx-text-to-audio/#input-duration) `duration` | number optional Allowed: 1 to 120 Default: `30` Length in seconds, 1-120 (30 by default); the price is $0.0206 an audio whatever the length |
| [#](https://flymy.ai/mcp/models/stable-audio-3-small-sfx-text-to-audio/#input-seed) `seed` | integer optional Allowed: 0 to 2147483647 Seed for a repeatable result |
| [#](https://flymy.ai/mcp/models/stable-audio-3-small-sfx-text-to-audio/#input-num_inference_steps) `num_inference_steps` | integer optional Allowed: 1 to 100 Default: `8` Sampling steps, 1-100 (8 by default): this distilled model gains little from more |
| [#](https://flymy.ai/mcp/models/stable-audio-3-small-sfx-text-to-audio/#input-output_format) `output_format` | string optional Allowed: mp3, wav, flac, ogg, opus, m4a, aac Default: `mp3` File format: mp3 (the default, 192 kbit/s), lossless wav or flac, or ogg, opus, m4a or aac |

## Ask your agent

Requests to paste as they are, once the FlyMy.AI MCP is connected.

**“Make 20 seconds of rain on a metal roof with Stable Audio 3 Small SFX.”** runs `flymyai/stable-audio-3-small-sfx-text-to-audio`

**“Use Stable Audio 3 Small SFX to generate three variations of a heavy wooden door creaking open.”** runs `flymyai/stable-audio-3-small-sfx-text-to-audio`

**“Create a busy city street ambience for a video scene with Stable Audio 3 Small SFX, with no music or voices.”** runs `flymyai/stable-audio-3-small-sfx-text-to-audio`

## Stable Audio 3 Small SFX price

$0.0206 per run. A run at the default settings costs $0.0206. Billed to your FlyMy.AI balance; no seats, no subscription and no minimum.

[See usage pricing →](https://flymy.ai/pricing/)

## Call Stable Audio 3 Small SFX from code

The same model, from an agent or from your own code. Keys stay in your FlyMy.AI account.

### From an agent, through the MCP

The agent calls `get_model_schema`, then `run_model` with:

```
{
  "endpoint_id": "flymyai/stable-audio-3-small-sfx-text-to-audio",
  "input": {
    "prompt": "Rain on a metal roof with distant thunder"
  }
}
```

### From your code, over HTTP

Form fields, not JSON; files go as uploads or public URLs. The answer is a `prediction_id`; read the result at `https://api.flymy.ai/api/v1/flymyai/stable-audio-3-small-sfx-text-to-audio/predict/async/result/?request_id=<prediction_id>`.

```
curl -X POST https://api.flymy.ai/api/v1/flymyai/stable-audio-3-small-sfx-text-to-audio/predict/async/ \
  -H "X-API-KEY: $FLYMYAI_API_KEY" \
  -F 'prompt=Rain on a metal roof with distant thunder'
```

## Questions about Stable Audio 3 Small SFX

**Do I need a Stability AI API key for Stable Audio 3 Small SFX?**

No. Stable Audio 3 Small SFX runs on FlyMy.AI's account, so you need no Stability AI key or plan: sign in to FlyMy.AI once and each run is billed to your FlyMy.AI balance.

**How much does Stable Audio 3 Small SFX cost?**

$0.0206 per run. There is no subscription or minimum; the price comes from FlyMy.AI billing and was checked on 2026-11-18.

**How do I use Stable Audio 3 Small SFX in Claude Code, Codex or Cursor?**

Add the FlyMy.AI MCP with one command and sign in, then ask in plain words, for example: "Make 20 seconds of rain on a metal roof with Stable Audio 3 Small SFX." Your agent reads the inputs with get_model_schema and runs flymyai/stable-audio-3-small-sfx-text-to-audio with run_model.

**What does Stable Audio 3 Small SFX need as input?**

Stable Audio 3 Small SFX requires prompt; it also takes 5 optional inputs, each listed on this page with its allowed values and default.

**Can I call Stable Audio 3 Small SFX from my own code?**

Yes. Send form fields to https://api.flymy.ai/api/v1/flymyai/stable-audio-3-small-sfx-text-to-audio/predict/async/ with your FlyMy.AI API key in the X-API-KEY header.

## More voice, music and sound models

Read text aloud, clone a voice from a short sample, turn lyrics or a prompt into a song, compose instrumentals, make sound effects from a description or for a video, or repair and extend a track.

### Stable Audio 3 Medium

Stability AI's music model for backing tracks, loops and intros: stereo, up to 6 minutes, one flat price.

Instrumental music / $0.0376 / run

Link: https://flymy.ai/mcp/models/stable-audio-3-medium-text-to-audio/

### Stable Audio 3 Medium Inpainting

Replace a section of your track: mark the seconds, say what should play there, keep the rest.

Audio inpainting / $0.0442 / run

Link: https://flymy.ai/mcp/models/stable-audio-3-medium-audio-inpainting/

### Stable Audio 3 Medium Outpainting

Lengthen a track or add an intro or an ending: new audio before the start or after the end.

Audio extension / $0.0446 / run

Link: https://flymy.ai/mcp/models/stable-audio-3-medium-audio-outpainting/

### Stable Audio 3 Small Music

The lightweight Stable Audio 3: cheap background music and loops of up to 2 minutes.

Instrumental music / $0.0217 / run

Link: https://flymy.ai/mcp/models/stable-audio-3-small-music-text-to-audio/

### Stable Audio 3 Small Music Inpainting

Lightweight music editing: regenerate one marked passage of a track of up to 2 minutes.

Audio inpainting / $0.026 / run

Link: https://flymy.ai/mcp/models/stable-audio-3-small-music-audio-inpainting/

### Stable Audio 3 Small Music Outpainting

Lightweight track extension: add up to 120 seconds of new music before or after your own.

Audio extension / $0.0265 / run

Link: https://flymy.ai/mcp/models/stable-audio-3-small-music-audio-outpainting/

## Go to the source

[Stable Audio 3 Small SFX in the playground →](https://app.flymy.ai/models/flymyai/stable-audio-3-small-sfx-text-to-audio), [Model endpoints in the docs →](https://docs.flymy.ai/api/models-endpoints), [Every model on FlyMy.AI →](https://flymy.ai/mcp/models/), [Every MCP in the catalog →](https://flymy.ai/mcp/#catalog), [Usage pricing →](https://flymy.ai/pricing/)

From the FlyMy.AI model catalog of 2026-11-18: inputs from the model's live schema, prices from FlyMy.AI billing. Requests are examples to paste, not recorded runs.

---

For agents: the FlyMyAI operating guide (sign up, connect, run models, tools and agents) is https://flymy.ai/skill.md, and https://flymy.ai/llms.txt lists the other pages and the documentation.
