Appearance

ACE-Step

POST/v1/run

Ace Step Audio Inpaint by ace - advanced AI model for audio-to-audio. Delivers high-quality results with fast inference, suitable for both creative and production workflows.

Request body

Submit an async generation request. The model field selects the model; other fields are model-specific input parameters.

stringmodelrequired

Model identifier. Set to ace/ace-step/audio-inpaint.

Default: ace/ace-step/audio-inpaint

Optional<string>audio

URL of the audio file to be inpainted.

Optional<string>lyrics

Lyrics to be sung in the audio. If not provided or if [inst] or [instrumental] is the content of this field, no lyrics will be sung. Use control structures like [verse], [chorus] and [bridge] to control the structure of the song.

Default:

Optional<number>guidance_scale

Guidance scale for the generation.

Range: 0 to 200

Default: 15

Optional<integer>seed

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

Optional<string>guidance_type

Type of CFG to use for the generation process.

Allowed values: cfg, apg, cfg_star

Default: apg

Optional<string>tags

Comma-separated list of genre tags to control the style of the generated audio.

Optional<integer>granularity_scale

Granularity scale for the generation process. Higher values can reduce artifacts.

Range: -100 to 100

Default: 10

Optional<string>scheduler

Scheduler to use for the generation process.

Allowed values: euler, heun

Default: euler

Optional<number>guidance_interval

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

Default: 0.5

Optional<number>minimum_guidance_scale

Minimum guidance scale for the generation after the decay.

Range: 0 to 200

Default: 3

Optional<number>start_time

start time in seconds for the inpainting process.

Range: 0 to 240

Default: 0

Optional<number>lyric_guidance_scale

Lyric guidance scale for the generation.

Range: 0 to 10

Default: 1.5

Optional<integer>number_of_steps

Number of steps to generate the audio.

Range: 3 to 60

Default: 27

Optional<number>variance

Variance for the inpainting process. Higher values can lead to more diverse results.

Range: 0 to 1

Default: 0.5

Optional<number>end_time

end time in seconds for the inpainting process.

Range: 0 to 240

Default: 30

Optional<number>guidance_interval_decay

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

Default: 0

Optional<string>start_time_relative_to

Whether the start time is relative to the start or end of the audio.

Allowed values: start, end

Default: start

Optional<number>tag_guidance_scale

Tag guidance scale for the generation.

Range: 0 to 10

Default: 5

Optional<string>end_time_relative_to

Whether the end time is relative to the start or end of the audio.

Allowed values: start, end

Default: start

Response Schema

The submit endpoint returns an accepted generation task. Poll the result endpoint with the returned id for terminal outputs or errors.

Optional<string>error

Error message if the task failed. Empty on success.

stringidrequired

Unique identifier for the generation task.

Optional<string>model

Model ID used for the prediction.

Optional<array>outputs

Array of generated content. Empty when status is not completed.

stringstatusrequired

Status of the task: pending, running, completed, failed, or timeout.

Allowed values: pending, running, completed, failed, timeout

Model capabilities

array<string>capability_tagsrequired

Capabilities declared by the model registry.

Default: audio-to-audio

stringexecution_moderequired

Execution mode declared by the model registry.

Default: async