How long can the tracks be?

1 to 380 seconds. You choose the length before you press go, and the price follows it.

How is it different from Stable Audio 2.5 and Stable Audio 3 Small SFX?

Stable Audio 3 Medium: Stereo music up to six minutes long, trained on licensed data. Stable Audio 2.5: Instrumental music and sound up to three minutes long. Stable Audio 3 Small SFX: A small, fast sound-effects model, trained on licensed data. They all run in the same studio, so you can try one prompt on each.

How much does a run cost?

A track costs $0.051. You see the exact price before you press go, and a run that fails costs nothing.

Is Stable Audio 3 Medium free to try?

No. There is no free credit: you add credit from $5, and your first top-up has no card fee. The cheapest run is $0.051 (a track), so $5 covers 98 of those. You pay per run, in dollars, with no subscription.

Can I use what I make commercially?

Yes. You own what you make on Leap, so you can use it commercially, and we never train AI on it. The people and brands shown in a result can still have rights in it; the Terms say more.

Yes. Leap's REST API runs it as stability-ai/stable-audio-3-medium, at the same price per run as the studio, and agents can call it through Leap's MCP server. The request is at the bottom of this page.

Do I need a Stability AI account?

No. Leap sends your request to Stability AI's model and gives you what it makes. One Leap account runs Stable Audio 3 Medium and every other model, in the studio, through the API and from your agents.

Stable Audio 3 MediumAI music generator

Stereo music up to six minutes long, trained on licensed data. On Leap, it sits beside 174 other models in one studio.

Music
Up to 380 s

No subscription
Every top model, one account
Pay per run, priced before it starts

Listen / A Balkan brass band in 7/8

0 / 30 s

Listen / Desert blues

0 / 30 s

AI music generator

Stable Audio 3 Medium at a glance

Stable Audio 3 Medium is a music model from Stability AI. It makes music from words, 1 to 380 seconds long.

Made by: Stability AI
Makes: Music
Starts from: Words
Length: 1 to 380 seconds
Prompt: Up to 4,000 characters
Price per run: $0.051
Updated: October 5, 2026

01Write the words, pick a voice
02See the exact price, then press go
03Keep it in your library, or take it further

Pick the right one

Stable Audio 3 Medium and its siblings

Model	Best for	Length	Price per run
Stable Audio 3 Medium (this page)	Stereo music up to six minutes long, trained on licensed data.	1 to 380 seconds	$0.051
Stable Audio 2.5	Instrumental music and sound up to three minutes long.	1 to 190 seconds	$0.27
Stable Audio 3 Small SFX	A small, fast sound-effects model, trained on licensed data.	1 to 120 seconds	$0.028

Start with an idea

Three ways to try Stable Audio 3 Medium

Side by side

More voice and sound models on Leap

Why Leap

Why creators make it on Leap

01
Every top model, side by side
175 models from Black Forest Labs, Google, ByteDance, Kuaishou, Alibaba and more, side by side in one studio.
See the models
02
One click, or full control
Character Studio, effects and recipes write the prompt for you. Or write your own for any model.
See the tools
03
Your work stays yours
Everything you make stays in your library while your account is active, and you own what you make here.
See what people make
04
One balance for everything
The studio, the API and your agents spend the same balance, and every run shows its price before it starts.
How pricing works

Questions

Stable Audio 3 Medium, answered

What is Stable Audio 3 Medium?: Stable Audio 3 Medium is a music model from Stability AI. Stereo music up to six minutes long, trained on licensed data. On Leap it runs in one studio beside every other top model, with one account.
How long can the tracks be?: 1 to 380 seconds. You choose the length before you press go, and the price follows it.
How is it different from Stable Audio 2.5 and Stable Audio 3 Small SFX?: Stable Audio 3 Medium: Stereo music up to six minutes long, trained on licensed data. Stable Audio 2.5: Instrumental music and sound up to three minutes long. Stable Audio 3 Small SFX: A small, fast sound-effects model, trained on licensed data. They all run in the same studio, so you can try one prompt on each.
How much does a run cost?: A track costs $0.051. You see the exact price before you press go, and a run that fails costs nothing.
Is Stable Audio 3 Medium free to try?: No. There is no free credit: you add credit from $5, and your first top-up has no card fee. The cheapest run is $0.051 (a track), so $5 covers 98 of those. You pay per run, in dollars, with no subscription.
Can I use what I make commercially?: Yes. You own what you make on Leap, so you can use it commercially, and we never train AI on it. The people and brands shown in a result can still have rights in it; the Terms say more.
Is there an API?: Yes. Leap's REST API runs it as stability-ai/stable-audio-3-medium, at the same price per run as the studio, and agents can call it through Leap's MCP server. The request is at the bottom of this page.
Do I need a Stability AI account?: No. Leap sends your request to Stability AI's model and gives you what it makes. One Leap account runs Stable Audio 3 Medium and every other model, in the studio, through the API and from your agents.

Your idea, Stable Audio 3 Medium.

Every run shows its price before it starts, and one that fails costs nothing.

Make it with Stable Audio 3 Medium

For developers

Run Stable Audio 3 Medium from code

API docs

Model ID: stability-ai/stable-audio-3-medium
Makes: Voice and sound
Pricing: Per run, quoted first: POST /v1/quotes

Inputs

What the model takes. Leave out anything with a default.

Promptprompt

Text, up to 4,000 characters, required

Durationduration

1 to 380, required. Default: 30 s

Num Inference Stepssettings.num_inference_steps

1 to 100. Default: 8Number of sampling steps.

Guidance Scalesettings.guidance_scale

0 to 25. Default: 1Classifier-free guidance scale.

Enable Prompt Expansionsettings.enable_prompt_expansion

On or off. Default: offIf True, the prompt will be expanded using an LLM for more detailed and higher quality results.

Negative promptnegative_prompt

Text, up to 2,000 charactersWhat the image should not contain.

Seedseed

0 to 4294967295The same seed and input give the same image.

The request

The same envelope for every model; only the model and its input change. With prefer: wait=60 the answer holds the result when the run finishes within a minute; a longer one is read again by its ID. Agents can call it through the MCP server at app.tryleap.ai/api/mcp.

curl https://api.tryleap.ai/v1/generations \  -H "x-api-key: $LEAP_API_KEY" \  -H "content-type: application/json" \  -H "prefer: wait=60" \  -d '{    "model": "stability-ai/stable-audio-3-medium",    "input": {      "prompt": "A paper boat drifting down a rainy street at dusk"    }  }' # Video often outlasts the wait and answers "queued" or "running".# Put its "id" in GENERATION_ID and read it again until it is done:# curl https://api.tryleap.ai/v1/generations/$GENERATION_ID -H "x-api-key: $LEAP_API_KEY"