Start creating

ACE Studio

ACE-StepAI music generator

Open-weight songs from genre tags and lyrics, priced by the second. On Leap, it sits beside 174 other models in one studio.

  • Music
  • Up to 240 s

60 s on ACE-Step: $0.0162. Your words wait while you sign in.

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

Listen / Lo-fi boom bap, 86 bpm

0 / 60 s

Listen / Flamenco guitar and palmas

0 / 45 s

AI music generator

ACE-Step at a glance

ACE-Step is a music model from ACE Studio. It makes music from words, 5 to 240 seconds long.

Made by
ACE Studio
Makes
Music
Starts from
Words
Length
5 to 240 seconds
Prompt
Up to 4,000 characters
Price per run
$0.00135 to $0.0648
Updated
October 3, 2026
  1. 01Write the words, pick a voice
  2. 02See the exact price, then press go
  3. 03Keep it in your library, or take it further

Start with an idea

Three ways to try ACE-Step

Side by side

More voice and sound models on Leap

Why Leap

Why creators make it on Leap

  1. 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
  2. 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
  3. 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
  4. 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

ACE-Step, answered

What is ACE-Step?
ACE-Step is a music model from ACE Studio. Open-weight songs from genre tags and lyrics, priced by the second. On Leap it runs in one studio beside every other top model, with one account.
How long can the tracks be?
5 to 240 seconds. You choose the length before you press go, and the price follows it.
How much does a run cost?
A 60-second track costs $0.0162 at the default settings. By length, a run costs $0.00135 to $0.0648. You see the exact price before you press go, and a run that fails costs nothing.
Is ACE-Step 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 $0.00135 (a 5-second track), so $5 covers 3703 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 ace-step/ace-step, 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 an ACE Studio account?
No. Leap sends your request to ACE Studio's model and gives you what it makes. One Leap account runs ACE-Step and every other model, in the studio, through the API and from your agents.

Your idea, ACE-Step.

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

Make it with ACE-Step

For developers

Run ACE-Step from code

API docs
Model ID
ace-step/ace-step
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
5 to 240, required. Default: 60 s
Lyricssettings.lyrics
Text, up to 4,000 charactersLyrics to be sung in the audio.
Number Of Stepssettings.number_of_steps
3 to 60. Default: 27Number of steps to generate the audio.
Schedulersettings.scheduler
Euler, Heun. Default: EulerScheduler to use for the generation process.
Guidance Typesettings.guidance_type
Cfg, Apg, Cfg star. Default: ApgType of CFG to use for the generation process.
Granularity Scalesettings.granularity_scale
-100 to 100. Default: 10Granularity scale for the generation process.
Guidance Intervalsettings.guidance_interval
0 to 1. Default: 0.5Guidance interval for the generation.
Guidance Interval Decaysettings.guidance_interval_decay
0 to 1. Default: 0Guidance interval decay for the generation.
Guidance Scalesettings.guidance_scale
0 to 200. Default: 15Guidance scale for the generation.
Minimum Guidance Scalesettings.minimum_guidance_scale
0 to 200. Default: 3Minimum guidance scale for the generation after the decay.
Tag Guidance Scalesettings.tag_guidance_scale
0 to 10. Default: 5Tag guidance scale for the generation.
Lyric Guidance Scalesettings.lyric_guidance_scale
0 to 10. Default: 1.5Lyric guidance scale for the generation.
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: $LEAP_API_KEY" \  -H "content-type: application/json" \  -H "prefer: wait=60" \  -d '{    "model": "ace-step/ace-step",    "input": {      "prompt": "A paper boat drifting down a rainy street at dusk"    }  }' # Video often outlasts the wait and answers "queued" or "running".# Put its "id" in GENERATION_ID and read it again until it is done:# curl https://api.tryleap.ai/v1/generations/$GENERATION_ID -H "x-api-key: $LEAP_API_KEY"