How to Use Stable Audio 3 Small SFX Text to Audio in Muse Code
Use Stable Audio 3 Small SFX Text to Audio for sound effects described in words, from drawer slams to environmental sounds. Unlike Stable Audio 3 Small SFX Audio to Audio, it starts without a recording.
Prompts to try with Stable Audio 3 Small SFX Text to Audio in Muse Code
Copy an example into Muse Code, or ask in your own words.
Inspect the game's door interactions and use Stable Audio 3 Small SFX Text to Audio to generate a 3-second wooden door slam: heavy impact, short hinge rattle, close microphone, dry room. Save it beside the existing sound assets.
Review the app's confirmation interaction and use Stable Audio 3 Small SFX Text to Audio to make a 1-second soft wooden tap with a fast decay. Add it to the prototype's audio assets for review.
Use Stable Audio 3 Small SFX Text to Audio to make a 20-second sound bed for the project's workshop scene: steady ventilation, intermittent distant metal clinks, close bench creaks, no musical elements.
Make a 3-second whoosh with Stable Audio 3 Small SFX Text to Audio for a menu transition in my app. Save the result in ./assets.
Create rain on a tin roof with distant thunder with Stable Audio 3 Small SFX Text to Audio, 20 seconds, for a video background.
How to set up Stable Audio 3 Small SFX Text to Audio in Muse Code
Pick the way that suits you. Each takes about two minutes.
Use Spiral's MCP server
- Install Muse Code
curl -fsSL https://dev.meta.ai/install.sh | bash
- Ask Muse to add the server
Start muse and ask:
Add the Spiral MCP server at https://api.spiral.ai/mcp
- Sign in
In your terminal, run:
muse mcp login spiral
Use the Spiral skill
- Send Muse Code this message
Your agent reads Spiral's skill and sets itself up.
set up https://spiral.ai/SKILL.md
- Sign in or paste a key
Approve Spiral in the browser, or give the agent a key from the console.
Use the Spiral CLI
- Install and sign in
Installs the Spiral CLI, signs you in and adds its skill to your coding agents.
npx -y spiral-cli@latest init
Call the Spiral API
- Create an API key
In the console, under API keys.
- Run Stable Audio 3 Small SFX Text to Audio
One request; the result comes back by polling or a webhook.
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-3/small/sfx/text-to-audio", "input": { "prompt": "An anthemic Pop Rock instrumental that fills your head with nostalgic thoughtfulness" } }'
Then paste one of the prompts above: Muse Code finds Stable Audio 3 Small SFX Text to Audio on Spiral, shows the price and runs it.
Stable Audio 3 Small SFX Text to Audio providers and prices
Spiral runs Stable Audio 3 Small SFX Text to Audio through fal. Open a card for today's price, with every fee included.
Settings you can ask for
Stable Audio 3 Small SFX Text to Audio works from your prompt. Ask Muse Code for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Negative prompt | what to leave out, in words | Text description of qualities to avoid in the output. | |
| Duration | 1 to 120 | 30 | Duration of the generated audio in seconds. |
| Number of inference steps | 1 to 100 | 8 | Number of sampling steps. Post-trained (distilled) checkpoints look good with the default 8 and gain little from going higher. |
| Guidance scale | 0 to 25 | 1 | Classifier-free guidance scale. Higher values follow the prompt more strictly. Only effective on base (non-distilled) checkpoints. |
| Seed | a whole number | Random seed for reproducible outputs. Omit for a random seed. | |
| Enable prompt expansion | on or off | off | If True, the prompt will be expanded using an LLM for more detailed and higher quality results. |
| Output format | mp3, wav, flac, ogg, opus, m4a, or aac | mp3 | Container format for the generated audio output. |
Every API field of Stable Audio 3 Small SFX · Text to Audio is on its tool page: open its card above.
What can you do with Stable Audio 3 Small SFX Text to Audio in Muse Code?
Turn a project's sound brief into effects for game actions, app feedback, and scene atmosphere with Stable Audio 3 Small SFX. A coding agent can inspect the relevant interactions, draft specific descriptions, and organize generated takes for review.
Game interaction sounds
Create short door slams, chest closures, and item drops. Describe the material, impact, and decay; use a source recording when reworking an existing effect.
Foley for short films
Make individual drawer thuds, chair scrapes, or footsteps for a scene. Generate from a description or reinterpret a rough recording, then place the selected sounds in the edit.
Environmental sound beds
Build rain, harbor, or workshop atmosphere for a scene. Describe nearby and distant sound sources, or rework a recording toward the desired setting.
App feedback sounds
Explore brief mechanical clicks, soft taps, and muted confirmation tones for product prototypes. Start with a description or reshape an existing sound.
Podcast scene effects
Add a kettle hiss, creaking door, or distant train to an audio story. Keep each effect separate from the spoken track for editing.
Trailer impacts and transitions
Explore heavy impacts, slowing mechanical sounds, and short metallic tails. Specify the source and processing rather than asking only for a dramatic sound.
More on Stable Audio 3 Small SFX Text to Audio and Muse Code
Overview
Stable Audio 3 Small SFX Text to Audio in other agents
Questions about Stable Audio 3 Small SFX Text to Audio in Muse Code
Can Muse Code use Stable Audio 3 Small SFX Text to Audio?
Yes. Add Spiral to Muse Code as an MCP server, and Muse Code can find and run Stable Audio 3 Small SFX Text to Audio like any built-in tool.
How much does Stable Audio 3 Small SFX Text to Audio cost in Muse Code?
$0.02678 per run at the default inputs. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Muse Code plan is separate.
Do I need a fal account to use Stable Audio 3 Small SFX Text to Audio in Muse Code?
No. Spiral runs Stable Audio 3 Small SFX Text to Audio on its own fal account. You sign in to Spiral once and never paste a key.
How long does it take to set up Stable Audio 3 Small SFX Text to Audio in Muse Code?
About two minutes: install Muse Code, then ask Muse to add the server, then sign in.
Does Muse Code wait while Stable Audio 3 Small SFX Text to Audio runs?
Stable Audio 3 Small SFX Text to Audio runs in the background. Muse Code starts the run, checks on it and gives you the audio when it's ready.
What is Stable Audio 3 Small SFX best for?
Use it for sound effects, one-shots, and environmental sound design. Its specialization is sound effects rather than music.
How long can Stable Audio 3 Small SFX audio be?
It supports up to 120 seconds. Choose a length that suits the event, such as a few seconds for a slam, rather than stretching a brief effect across two minutes.
Can Stable Audio 3 Small SFX generate narration or dialogue?
It is not designed for speech or voice generation. Use it for the effects around a scene and choose a speech model for spoken lines.
What language should I use for prompts?
Write descriptions in English. The maker says prompts in other languages underperform.
How should I describe a sound effect?
Name the object or source, describe what happens and how the sound decays, then specify the recording character. For example, describe a wooden drawer slamming shut with a heavy thud, a short tail, and close microphone placement in a dry room.
Start using Stable Audio 3 Small SFX Text to Audio in Muse Code
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into Muse Code:
set up https://spiral.ai/SKILL.md


