ace modelsaudio generation api

ace/ace-step/prompt-to-audio

Name: ACE-Step
Author: ace

Ace Step Prompt To Audio by ace - generate music, sound effects, and audio from text descriptions with AI. Create original compositions, ambient sounds, and audio content for any creative project.

Input

Prompt(string)

Prompt to control the style of the generated audio. This will be used to generate tags and lyrics.

Duration(integer)

5240

The duration of the generated audio in seconds. Range: 5 to 240.

Guidance Scale(number)

0200

Guidance scale for the generation. Range: 0 to 200.

Seed(integer)

Random seed for reproducibility. If not provided, a random seed will be used.

Guidance Type(string)

Type of CFG to use for the generation process. Allowed values: cfg, apg, cfg_star.

Granularity Scale(integer)

-100100

Granularity scale for the generation process. Higher values can reduce artifacts. Range: -100 to 100.

Number Of Steps(integer)

360

Number of steps to generate the audio. Range: 3 to 60.

Lyric Guidance Scale(number)

010

Lyric guidance scale for the generation. Range: 0 to 10.

Instrumental(boolean)

Whether to generate an instrumental version of the audio.

Tag Guidance Scale(number)

010

Tag guidance scale for the generation. Range: 0 to 10.

Guidance Interval Decay(number)

Guidance interval decay for the generation. Guidance scale will decay from guidance_scale to min_guidance_scale in the interval. 0.0 means no decay. Range: 0 to 1.

Scheduler(string)

Scheduler to use for the generation process. Allowed values: euler, heun.

Guidance Interval(number)

Guidance interval for the generation. 0.5 means only apply guidance in the middle steps (0.25 * infer_steps to 0.75 * infer_steps) Range: 0 to 1.

Minimum Guidance Scale(number)

0200

Minimum guidance scale for the generation after the decay. Range: 0 to 200.

Idle

Example output — click Run to generate your own

Production endpoint

Send your first request

OpenAI-compatible endpoint with unified authentication and usage tracking.

POSThttps://api.sandbase.ai/v1/run

Model IDace/ace-step/prompt-to-audio

Input Schema

14 parameters · 1 required · 13 optional

Parameter	Type	Required	Description
`prompt`	string	Required	Prompt to control the style of the generated audio. This will be used to generate tags and lyrics.
`seed`	integer	Optional	Random seed for reproducibility. If not provided, a random seed will be used.
`duration`	integer	Optional	The duration of the generated audio in seconds. · Min: 5 · Max: 240 · Default: 60
`scheduler`	string	Optional	Scheduler to use for the generation process. · Options: euler, heun · Default: "euler" eulerheun
`instrumental`	boolean	Optional	Whether to generate an instrumental version of the audio. · Default: false
`guidance_type`	string	Optional	Type of CFG to use for the generation process. · Options: cfg, apg, cfg_star · Default: "apg" cfgapgcfg_star
`guidance_scale`	number	Optional	Guidance scale for the generation. · Min: 0 · Max: 200 · Default: 15
`number_of_steps`	integer	Optional	Number of steps to generate the audio. · Min: 3 · Max: 60 · Default: 27
`granularity_scale`	integer	Optional	Granularity scale for the generation process. Higher values can reduce artifacts. · Min: -100 · Max: 100 · Default: 10
`guidance_interval`	number	Optional	Guidance interval for the generation. 0.5 means only apply guidance in the middle steps (0.25 * infer_steps to 0.75 * infer_steps) · Min: 0 · Max: 1 · Default: 0.5
`tag_guidance_scale`	number	Optional	Tag guidance scale for the generation. · Min: 0 · Max: 10 · Default: 5
`lyric_guidance_scale`	number	Optional	Lyric guidance scale for the generation. · Min: 0 · Max: 10 · Default: 1.5
`minimum_guidance_scale`	number	Optional	Minimum guidance scale for the generation after the decay. · Min: 0 · Max: 200 · Default: 3
`guidance_interval_decay`	number	Optional	Guidance interval decay for the generation. Guidance scale will decay from guidance_scale to min_guidance_scale in the interval. 0.0 means no decay. · Min: 0 · Max: 1 · Default: 0

Output Schema

Field	Type	Description
`id`	string	Unique identifier for the generation task
`status`	string	Task status: pending, running, completed, failed, timeout
`model`	string	Model used for the generation
`outputs`	array	Array of output items
`outputs[].url`	string	URL of the generated artifact
`outputs[].content_type`	string	MIME type (e.g. image/png, video/mp4)
`error`	object \| null	Error details if failed, null on success
`error.type`	string	Machine-readable error type code
`error.message`	string	Human-readable error description

Async Workflow

This model uses asynchronous execution. Submit a request and poll for the result.

Submit — POST to /v1/run, receive an id
Poll — GET /v1/run/{id} until status is completed, failed, or timeout
Retrieve — Read outputs from the completed response

Code Examples

Ready-to-run snippets

# Step 1: Submit
curl -X POST https://api.sandbase.ai/v1/run \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
  "model": "ace/ace-step/prompt-to-audio",
  "prompt": "A lofi hiphop song with a chill vibe about a sunny day on the boardwalk.",
  "duration": 60,
  "scheduler": "euler",
  "instrumental": false,
  "guidance_type": "apg",
  "guidance_scale": 15,
  "number_of_steps": 27,
  "granularity_scale": 10,
  "guidance_interval": 0.5,
  "tag_guidance_scale": 5,
  "lyric_guidance_scale": 1.5,
  "minimum_guidance_scale": 3,
  "guidance_interval_decay": 0
}'

# Step 2: Poll result (replace <id>)
curl https://api.sandbase.ai/v1/run/<id> \
  -H "Authorization: Bearer YOUR_API_KEY"

← Back to ACE-Step

API README

ACE-Step

ACE-Step Prompt-to-Audio turns a natural-language music brief into a generated track. The prompt can describe genre, instrumentation, tempo, mood, arrangement, and production character, allowing creators to begin with an idea rather than prepared lyrics or an existing recording.

The route can create instrumental music or let the model derive musical and lyrical direction from the prompt. Duration spans five seconds to four minutes, and seed, scheduler, inference steps, and guidance controls support repeatable exploration.

Highlights

Natural-language music creation. Translates a descriptive brief into an arranged audio track.

Instrumental option. Generates music without vocals when the project calls for a score, bed, or backing track.

Five seconds to four minutes. Covers stingers, loops, song sections, and longer-form ideas.

Tunable generation. Seed, scheduler, step count, and multiple guidance settings provide control beyond the prompt.

Pricing

Billing unit	Price
Per generated second	$0.0002

When to Use

✅ Good fit	❌ Consider alternatives
The model's named workflow matches the source material and intended output	A different input modality or model route is required
A managed asynchronous result is suitable for the production pipeline	A synchronous, interactive editor is essential
The documented controls cover the required duration, framing, or format	The project needs controls outside this endpoint's schema
Creative iteration benefits from a repeatable request structure	Exact deterministic pixels, frames, geometry, or samples are mandatory
A finished downloadable media asset is the desired deliverable	Editable source layers or a native project file are required

Prompt Guide

For music generation, state the intended result first, then add the subject or source treatment, progression, style, and delivery constraints. Keep one creative variable per phrase, use the documented field names for controls, and change one setting at a time when comparing results.

{
  "duration": 60,
  "prompt": "A lofi hiphop song with a chill vibe about a sunny day on the boardwalk."
}

Technical Specs

Spec	Value
Model ID	`ace/ace-step/prompt-to-audio`
Inputs	duration, granularity_scale, guidance_interval, guidance_interval_decay, guidance_scale, guidance_type, instrumental, lyric_guidance_scale, minimum_guidance_scale, number_of_steps, prompt, scheduler, seed, tag_guidance_scale
Required inputs	prompt
Output fields	content_type, url
Execution	Async (submit, then poll for result)

Related Models

ace/ace-step — Compare a nearby route in the same local model family.
ace/ace-step/audio-inpaint — Compare a nearby route in the same local model family.
ace/ace-step/audio-outpaint — Compare a nearby route in the same local model family.