Stability: Stable Audio 3 Small SFX

Stable Audio 3 Small SFX is a 459 million parameter latent diffusion model that generates high-quality sound effects from text prompts, designed for on-device deployment on mobile phones and consumer laptops.

Compare models

stable-audio-3-small-sfx-text-to-audio

AvailableStabilityMusicAsync

Price: From $0.0206
Modalities: Audio

About Stable Audio 3 Small SFX

Stable Audio 3 Small SFX is the sound-effects checkpoint of the Small tier in Stability AI's Stable Audio 3 family. It is a 459 million parameter latent diffusion model for high-quality effects from text, designed to run on phones and consumer laptops. It is the one to use for effects. Small Music covers compositions, and the Base checkpoint is meant for fine-tuning.

Where it works well

Generates sound effects from plain English descriptions.
Stereo output and a stated duration, which suits exact-length cues.
Built to run on consumer-grade hardware, per the model card.

When to choose another model

It is not meant for full musical compositions; use Small Music or a larger model.
Effects length is limited, and long ambient beds may need stitching.

Getting started

Create API key
Create a key in Console, then use it with every model on the platform.

Send your first request

Copy the example for your language and run it against the endpoint.

MusicTokenLab endpoint

POST/v1/music/generations

curl -X POST "https://api.tokenlab.sh/v1/music/generations" \
  -H "Authorization: Bearer sk-xxx" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "stable-audio-3-small-sfx-text-to-audio",
  "prompt": "Warm ambient piano with subtle rain textures.",
  "title": "Evening Drift"
}'

Pricing

Official price is the model maker's public baseline. TokenLab price is what you pay for this model on TokenLab.

Music

per request

Official price: $0.0206
Official: $0.0206
Discount: —

	Official priceper request	Officialper request	Discount
Music	$0.0206	$0.0206	—

Usage & activity

Success rate is the share of requests that completed. Latency is how long a full response takes; P95 means 95% of requests finished within that time.

Usage & availability

Last 24 hours

Requests
Success rate
P95 latency
Total tokens

Model performance

Last updated Oct 3, 2026, 07:26 PM UTC

Metrics appear once privacy and data volume thresholds are met.

Data is based on aggregate user requests, excluding status checks.

Open in Console

Open Stable Audio 3 Small SFX in Console with a prompt ready to edit or send.

Help me create with stable-audio-3-small-sfx-text-to-audio using music at /v1/music/generations. Show the result, status, and cost.

Use cases

Game audio
Create footsteps, impacts, pickups, and interface sounds from written descriptions, and choose the exact length each cue needs in the game.
Video post-production
Fill foley and ambience gaps in an edit by describing the missing sound and its duration, instead of searching a library.
App feedback sounds
Generate taps, confirmations, and alerts for a mobile or web interface, trying several variants of the same cue to find the right feel.
Podcast and ad stingers
Make short transitions, whooshes, and hits for podcasts and ads, specifying a length that matches the gap in the edit.

Prompt examples

Heavy wooden door creaking open in a stone hallway, echoing, 5 seconds.

Sci-fi UI confirm beep, soft and rising, 1 second.

Footsteps on gravel then wet grass, medium pace.

FAQ

What is Stable Audio 3 Small SFX?

A compact text-to-audio model from Stability AI focused on sound effects. It is a latent diffusion model designed for on-device deployment on mobile phones and consumer laptops.

How does Small SFX differ from the Base version?

The Base checkpoint lacks the adversarial post-training that speeds inference and raises quality, and is meant for fine-tuning. Use this standard Small SFX model when you want to generate effects directly.

Does Stable Audio 3 Small SFX produce stereo audio?

Yes, the model card says it generates stereo audio. It takes an English text prompt and a duration in seconds, so you can ask for effects that fit a precise gap in a video or game scene.

Can Small SFX also generate music?

Its design targets sound effects, so music is not what it is tuned for. For compositions, use Stable Audio 3 Small Music, or the larger Stable Audio 3 listing if you need longer or fuller pieces.

Can Small SFX run locally?

Stability says the model can run on consumer-grade hardware, including recent laptops, when you use the open weights. Calling it as a service needs no hosting on your side.

How much does Stable Audio 3 Small SFX cost?

On TokenLab, Stable Audio 3 Small SFX costs $0.0206 per request. The pricing table above shows the full breakdown. Rates depend on the billing unit, specification, and usage. Compare matching conditions in the model's detailed pricing; a single rate does not determine the total cost.

Which endpoint should Stable Audio 3 Small SFX use?

Use https://api.tokenlab.sh/v1/music/generations for Stable Audio 3 Small SFX. The request example below shows the matching code shape.

Which operations does Stable Audio 3 Small SFX support?

Stable Audio 3 Small SFX supports Music. Select an operation above to see its endpoint and request example.