Skip to content

ACE Step Audio Inpaint

Integrate

Model id ace-step/audio-inpaint
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://api.doitong.ru/v1/run/ace-step/audio-inpaint?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "audio": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3",
    "tags": "lofi, hiphop, drum and bass, trap, chill"
  }'

# Still "queued" or "running"? Poll with the id from the response:
curl "https://api.doitong.ru/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"

Files like the example: $0.002 2 API credits · ≈ ₽0.21 your files are measured before the run Run it on this page

Get API key
ACE Studio Text to Music #audio-to-audio#audio-inpaint#audio-repaint

Regenerates a chosen time window of an existing audio file using new tags and lyrics

ACE Studio · Audio

Your first result goes here

Build a request below and run it with your API key. Outputs are copied to our storage, kept forever or 7 days for free.

Build a request

Controls are generated from the model schema. The code and the price update as you change them.

•required audio_url
Drop a file, or

Audio file URL for inpainting.

•required

Audio style tags supplied as comma-separated genres, with `prompt` available as an alternative way to provide them.

Advanced lyrics · start_time_relative_to · end_time_relative_to · scheduler · guidance_type · start_time · end_time · variance · number_of_steps · granularity_scale · guidance_interval · guidance_interval_decay · guidance_scale · minimum_guidance_scale · tag_guidance_scale · lyric_guidance_scale · seed
default

Sung lyrics, with song sections organized using controls such as [verse], [chorus], and [bridge]. For audio without sung lyrics, omit this input or supply only [inst] or [instrumental].

start_time_relative_to default start

Reference point for the start time: either the audio's start or its end.

end_time_relative_to default start

Reference point for the end time: either the audio's start or its end.

scheduler default euler

Scheduler used during generation.

guidance_type default apg

CFG type used during generation.

default 0

Inpainting start time, measured in seconds.

default 30

Inpainting end time, measured in seconds.

default 0.5

Inpainting variance controls how diverse the results may be; increasing it can introduce more variation.

default 27

Step count used during audio generation.

default 10

Granularity scale applied during generation. Increasing it may reduce artifacts.

default 0.5

Portion of the generation schedule that receives guidance: choosing 0.5 restricts it to steps from 0.25 * infer_steps through 0.75 * infer_steps, leaving the beginning and end unguided.

default 0

Guidance decay within the generation interval: 0.0 keeps decay disabled; otherwise, the scale decreases over that interval from guidance_scale to min_guidance_scale.

default 15

Scale of guidance applied during generation.

default 3

Lowest guidance scale reached after decay during generation.

default 5

Scale of tag guidance applied during generation.

default 1.5

Scale of lyric guidance applied during generation.

Seed for reproducible generation, chosen randomly unless you supply a value.

POST /run/ace-step/audio-inpaint?wait=20 quote → $0.002
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://api.doitong.ru/v1/run/ace-step/audio-inpaint?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "audio": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3",
    "tags": "lofi, hiphop, drum and bass, trap, chill"
  }'

# Still "queued" or "running"? Poll with the id from the response:
curl "https://api.doitong.ru/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"

Run this request

Your key stays in this browser: it is sent only to the Doitong API and saved (localStorage) only if you tick Remember. Get an API key

About ACE Step Audio Inpaint

Takes an `audio_url` and rewrites only the section between `start_time` and `end_time`, each measured in seconds from 0 to 240. Each time can be set relative to the start or end of the clip. New `tags` and `lyrics` steer the replaced part, and `variance` controls how varied the result is. The usual guidance and step settings are available.

Parameters

Send either the canonical name or the native name, not both. Canonical names

NameType DefaultAllowed Description
audio_urlrequired audio
Typeurl · audio
Audio file URL for inpainting.
start_time_relative_tooptional
Typeenum
Defaultstart
startend
Reference point for the start time: either the audio's start or its end.
start_timeoptional
Typenumber
Default0
0 – 240
Inpainting start time, measured in seconds.
end_time_relative_tooptional
Typeenum
Defaultstart
startend
Reference point for the end time: either the audio's start or its end.
end_timeoptional
Typenumber
Default30
0 – 240
Inpainting end time, measured in seconds.
tagsrequired
Typestring
Audio style tags supplied as comma-separated genres, with `prompt` available as an alternative way to provide them.
lyricsoptional
Typestring
Default
Sung lyrics, with song sections organized using controls such as [verse], [chorus], and [bridge]. For audio without sung lyrics, omit this input or supply only [inst] or [instrumental].
varianceoptional
Typenumber
Default0.5
0 – 1
Inpainting variance controls how diverse the results may be; increasing it can introduce more variation.
number_of_stepsoptional
Typeinteger
Default27
3 – 60
Step count used during audio generation.
seedoptional
Typeinteger | null
Seed for reproducible generation, chosen randomly unless you supply a value.
scheduleroptional
Typeenum
Defaulteuler
eulerheun
Scheduler used during generation.
guidance_typeoptional
Typeenum
Defaultapg
cfgapgcfg_star
CFG type used during generation.
granularity_scaleoptional
Typeinteger
Default10
-100 – 100
Granularity scale applied during generation. Increasing it may reduce artifacts.
guidance_intervaloptional
Typenumber
Default0.5
0 – 1
Portion of the generation schedule that receives guidance: choosing 0.5 restricts it to steps from 0.25 * infer_steps through 0.75 * infer_steps, leaving the beginning and end unguided.
guidance_interval_decayoptional
Typenumber
Default0
0 – 1
Guidance decay within the generation interval: 0.0 keeps decay disabled; otherwise, the scale decreases over that interval from guidance_scale to min_guidance_scale.
guidance_scaleoptional
Typenumber
Default15
0 – 200
Scale of guidance applied during generation.
minimum_guidance_scaleoptional
Typenumber
Default3
0 – 200
Lowest guidance scale reached after decay during generation.
tag_guidance_scaleoptional
Typenumber
Default5
0 – 10
Scale of tag guidance applied during generation.
lyric_guidance_scaleoptional
Typenumber
Default1.5
0 – 10
Scale of lyric guidance applied during generation.
required Canonical name, also accepted

File parameters take a public https:// URL, a data: URI up to 10 MB, or the file_url of an upload. Files

Output

GET /requests/req_8k2m4q7x1z9c3v5b6n0p2r4t
{
  "id": "req_8k2m4q7x1z9c3v5b6n0p2r4t",
  "object": "request",
  "model": "ace-step/audio-inpaint",
  "status": "succeeded",
  "created_at": "2026-10-20T12:00:00Z",
  "started_at": "2026-10-20T12:00:02Z",
  "completed_at": "2026-10-20T12:00:09Z",
  "queue_position": null,
  "cost": {
    "credits": 2,
    "usd": "0.002",
    "charged": 2,
    "refunded": 0
  },
  "input": {
    "tags": "lofi, hiphop, drum and bass, trap, chill",
    "audio_url": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3"
  },
  "output": {
    "audio": {
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.mp3",
      "content_type": "audio/mpeg",
      "file_name": "0-output.mp3",
      "file_size": 1843200
    },
    "seed": 42,
    "tags": "lofi, hiphop, drum and bass, trap, chill",
    "lyrics": "[inst]"
  },
  "outputs": [
    {
      "type": "audio",
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.mp3",
      "content_type": "audio/mpeg",
      "file_size": 1843200,
      "duration": 12,
      "stored": true
    }
  ],
  "error": null,
  "metrics": {
    "inference_seconds": 6.8
  },
  "urls": {
    "self": "https://api.doitong.ru/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
    "cancel": "https://api.doitong.ru/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t/cancel"
  }
}
Your files, your choiceEvery outputs[].url is a copy on our storage: kept forever (paid per GB-month) or 7 days for free, by your account setting or ?storage=.
Same shape on every modeltype, url, content_type, width, height and duration, for images, video and audio alike. output is the model’s own result object.
Fields of output
audio
object {url, content_type, file_name, file_size}Audio file produced by generation.
seed
integerRandom seed used during generation.
tags
stringGenre tags applied during generation.
lyrics
stringLyrics applied during generation.

More models: Text to Music

For AI agents: this page as Markdown is at https://doitong.com/en-US/developers/models/ace-step/audio-inpaint.md. All models and guides: https://doitong.com/developers/llms.txt