Dža ko lil

ACE Step Audio To Audio

Integriruj

Modelosko id ace-step/audio-to-audio
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://api.doitong.com/v1/run/ace-step/audio-to-audio?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",
    "original_tags": "lofi, hiphop, drum and bass, trap, chill",
    "tags": "lofi, hiphop, drum and bass, trap, chill"
  }'

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

Fajlo sar o misalo: $0.002 2 API krediti tire fajlo si merime angl-o phiripen Phir les kate

Lel API klidin
ACE Studio · Audio

Tiro prvo rezultato si kate

Ker tele jekh mangipen thaj phir les tire API klidinosa. E rezultatur si kopirime amare arakhipneste, vično vaj 7 dives bilačhes.

Ker jekh mangipen

O kontrolura kerde si katar e schemaske. O kodo thaj e cena menjinen sar tu len menjines.

•trubul audio_url
Čhiv jekh fajl, vaj

Audio-fajlo URL vaš outpainting.

•trubul

Tago save originalno sas phandle e audio-fajloça.

•trubul

Audio-stilake tago dine komase genre, `prompt` si alternativno drom te den len.

Lučhe original_lyrics · lyrics · edit_mode · scheduler · guidance_type · number_of_steps · granularity_scale · guidance_interval · guidance_interval_decay · guidance_scale · minimum_guidance_scale · tag_guidance_scale · lyric_guidance_scale · seed · original_seed
standardno

Lava save originalno sas phandle e audio-fajloça.

standardno

Gilabde lava, e giliqe sekcije organizuime kontrolenca sar [verse], [chorus] thaj [bridge]. Audio bi gilabde lavenca, mukhen kada inputo khana den numa [inst] vaj [instrumental].

edit_mode standardno remix

Editiripeqo modo: paruv numa e lava vaj remixisar e audio.

scheduler standardno euler

Scheduler savo si utilizuime ko generiripe.

guidance_type standardno apg

CFG tipo savo si utilizuime ko generiripe.

standardno 27

Gengo gin savo si utilizuime ko audioqe generiripe.

standardno 10

Granularitetoski skala aplikovano ko generiripe. Lashi bari skala šaj te umalavel artefakto.

standardno 0.5

Porcija e generiripeqe schedule-eski savi lel guidance: te kidel 0.5, limitisarel la pe gengo steps-ende andar 0.25 * infer_steps dži 0.75 * infer_steps, bi guidance ko anglutno thaj agoruno.

standardno 0

Guidance decay ande generiripeqi intervala: 0.0 mukel decay biaktivno; averčes, e skala tele džal pe kada intervalo andar guidance_scale dži min_guidance_scale.

standardno 15

Guidance-qi skala aplikovano ko generiripe.

standardno 3

Najtele guidance-qi skala, savi arakhel pes palal decay ko generiripe.

standardno 5

Skala e tago guidance-i aplikovano ko generiripe.

standardno 1.5

Skala e lyric guidance-i aplikovano ko generiripe.

Seed vaš reproducibilno generiripe, randomno kidlo te na den valore.

Seed savo originalno sas phandle e audio-fajloça.

POST /run/ace-step/audio-to-audio?wait=20 hesab → $0.002
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://api.doitong.com/v1/run/ace-step/audio-to-audio?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",
    "original_tags": "lofi, hiphop, drum and bass, trap, chill",
    "tags": "lofi, hiphop, drum and bass, trap, chill"
  }'

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

Phandel kava mangipen

Tiro kluč ačhel kadale browsereste: bičhalel pes numa ko Doitong API thaj šuvav pes (localStorage) numa te tiknes Remember. Le jekh API ključ

Palal ACE Step Audio To Audio

Lokhel katar `audio_url` thaj lesko `original_tags`, thaj thovela neve `tags` te paruvav lesko stilo. `edit_mode` si remix, savo paruvavela sa o zvuko, vaj lyrics, savo editinela numa so gilabarel pes. Šaj te del `original_lyrics` thaj neve `lyrics`, thaj `original_seed` te džanel pes. E parametro vaš paso thaj lidžaripe si sar andi familija.

Parametra

Bičhalav vaj e kanonikano nav vaj e native nav, na duj. Kanonikane nava

NavTip standardnoMuklo Vakeripe
audio_urltrubul audio
Tipurl · audio
Audio-fajlo URL vaš outpainting.
edit_modeopcionalno
Tipenum
standardnoremix
lyricsremix
Editiripeqo modo: paruv numa e lava vaj remixisar e audio.
original_tagstrubul
Tipstring
Tago save originalno sas phandle e audio-fajloça.
original_lyricsopcionalno
Tipstring
standardno
Lava save originalno sas phandle e audio-fajloça.
tagstrubul
Tipstring
Audio-stilake tago dine komase genre, `prompt` si alternativno drom te den len.
lyricsopcionalno
Tipstring
standardno
Gilabde lava, e giliqe sekcije organizuime kontrolenca sar [verse], [chorus] thaj [bridge]. Audio bi gilabde lavenca, mukhen kada inputo khana den numa [inst] vaj [instrumental].
number_of_stepsopcionalno
Tipinteger
standardno27
3 – 60
Gengo gin savo si utilizuime ko audioqe generiripe.
seedopcionalno
Tipinteger | null
Seed vaš reproducibilno generiripe, randomno kidlo te na den valore.
scheduleropcionalno
Tipenum
standardnoeuler
eulerheun
Scheduler savo si utilizuime ko generiripe.
guidance_typeopcionalno
Tipenum
standardnoapg
cfgapgcfg_star
CFG tipo savo si utilizuime ko generiripe.
granularity_scaleopcionalno
Tipinteger
standardno10
-100 – 100
Granularitetoski skala aplikovano ko generiripe. Lashi bari skala šaj te umalavel artefakto.
guidance_intervalopcionalno
Tipnumber
standardno0.5
0 – 1
Porcija e generiripeqe schedule-eski savi lel guidance: te kidel 0.5, limitisarel la pe gengo steps-ende andar 0.25 * infer_steps dži 0.75 * infer_steps, bi guidance ko anglutno thaj agoruno.
guidance_interval_decayopcionalno
Tipnumber
standardno0
0 – 1
Guidance decay ande generiripeqi intervala: 0.0 mukel decay biaktivno; averčes, e skala tele džal pe kada intervalo andar guidance_scale dži min_guidance_scale.
guidance_scaleopcionalno
Tipnumber
standardno15
0 – 200
Guidance-qi skala aplikovano ko generiripe.
minimum_guidance_scaleopcionalno
Tipnumber
standardno3
0 – 200
Najtele guidance-qi skala, savi arakhel pes palal decay ko generiripe.
tag_guidance_scaleopcionalno
Tipnumber
standardno5
0 – 10
Skala e tago guidance-i aplikovano ko generiripe.
lyric_guidance_scaleopcionalno
Tipnumber
standardno1.5
0 – 10
Skala e lyric guidance-i aplikovano ko generiripe.
original_seedopcionalno
Tipinteger | null
Seed savo originalno sas phandle e audio-fajloça.
trubul Kanonikano nav, vi akceptime

Fajloske parametra lel jekh publikano https:// URL, jekh data: URI dži 10 MB, vaj e file_url uploadoski. Fajlura

Rezultato

GET /requests/req_8k2m4q7x1z9c3v5b6n0p2r4t
{
  "id": "req_8k2m4q7x1z9c3v5b6n0p2r4t",
  "object": "request",
  "model": "ace-step/audio-to-audio",
  "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",
    "original_tags": "lofi, hiphop, drum and bass, trap, chill"
  },
  "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.com/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
    "cancel": "https://api.doitong.com/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t/cancel"
  }
}
Tire fajlura, tiro alosaripenSako outputs[].url si kopija amare arakhipneste: vično (čargeime per GB-mase) vaj 7 dives bilačhes, tiro kontoskere regulaciatar vaj ?storage=.
Sa jekh forma sako modeloθartype, url, content_type, width, height thaj duration, varesave imajinake, video thaj audio-ke. output si o modelosko korkoro resultosko objekto.
Outputoske fieldura
audio
object {url, content_type, file_name, file_size}Audio-fajlo kerdino generiripeça.
seed
integerRandomno seed utilizuime ko generiripe.
tags
stringGenre-tago aplikovande ko generiripe.
lyrics
stringGilabde lava aplikovande ko generiripe.

Bute modeli: Teksto ko Muzika

AI agentenge: kadija rig sar Markdown si kate https://doitong.com/rom/developers/models/ace-step/audio-to-audio.md. Sa e modelura thaj e gidura: https://doitong.com/developers/llms.txt