Saltar al cuntegna

ACE Step Audio Outpaint

Integrar

ID dal model ace-step/audio-outpaint
# 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-outpaint?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"

Datotecas sco l'exempel: $0,006 6 credits API · ≈ ₽0,64 tias datotecas vegnan mesiradas avant l'execuziun Lantschar sin questa pagina

Obtegna ina clav API
ACE Studio Text a musica 0–107 s #audio-to-audio#audio-outpaint#audio-extend

Prolunghescha in clip audio existent avant il cumenzament u suenter la fin cun musica cumponida da nov

ACE Studio · Audio

Tes emprim resultat vegn qua

Construis ina dumonda sutvart e l'exequescha cun tia clav API. Outputs vegnan copiads en nossa memorisaziun, conservads per adina u 7 dis gratuitamain.

Construir ina dumonda

Ils controls vegnan generads dal schema dal model. Il code e ​​il pretsch s'actualiseschan durant che ti als midas.

•obligatori audio_url
Trametta in datoteca u

URL da la datoteca audio per l'outpainting.

•obligatori

Tags da stil audio furnids sco genres separads cun commas, cun `prompt` sco alternativa per als furnir.

standard 0

Durada da l'extensiun avant il cumenzament da l'audio, en secundas.

standard 30

Durada da l'extensiun suenter la fin da l'audio, en secundas.

Avanzà lyrics · 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
standard

Text chantà, cun las parts da la chanzun organisadas cun controllas sco [verse], [chorus] e [bridge]. Per audio senza text chantà, ometta quest input u furnescha mo [inst] u [instrumental].

scheduler standard euler

Scheduler utilisà durant la generaziun.

guidance_type standard apg

Tip CFG utilisà durant la generaziun.

standard 27

Dumber da pass utilisà durant la generaziun audio.

standard 10

Scala da granularitad applitgada durant la generaziun. Augmentarla po reducir artifacts.

standard 0.5

Part dal program da generaziun che survegn guida: la tscherna da 0.5 la restrenscha als pass da 0.25 * infer_steps fin a 0.75 * infer_steps, laschond l'inizial e la fin senza guida.

standard 0

Decadiment da la guida entaifer l'interval da generaziun: 0.0 lascha il decadiment disactivà; autramain sa reducescha la scala durant quest interval da guidance_scale a min_guidance_scale.

standard 15

Scala da la guida applitgada durant la generaziun.

standard 3

Scala minimala da la guida cuntanschida suenter il decadiment durant la generaziun.

standard 5

Scala da la guida da tags applitgada durant la generaziun.

standard 1.5

Scala da la guida dal text chantà applitgada durant la generaziun.

Seed per ina generaziun reproducibla, tschernì casualmain sche ti na furneschas nagina valur.

POST /run/ace-step/audio-outpaint?wait=20 calculaziun → $0,006
# 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-outpaint?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"

Executar questa dumonda

Tia clav resta en quest browser: ella vegn tramessa mo al Doitong API e memorisada (localStorage) mo sch'ella scheccas Tiar a memoria. Obtegnair ina clav API

Davart ACE Step Audio Outpaint

Continuescha ina musica furnida via `audio_url`. `extend_before_duration` e `extend_after_duration` agiuntan mintgamai fin a 107 secundas al cumenzament u a la fin, e la valur predefinida è 30 secundas suenter la fin. Il stil vegn da `tags`, cun `lyrics` opziunals per las parts agiuntadas. La quantitad da pass, il scheduler e las regulaziuns da guida correspundan als auters models ACE Step.

Parameters

Invia u il num canonic u il num nativ, betg omaduas. Nums canonics

NumTip StandardPermess Descripziun
audio_urlobligatori audio
Tipurl · audio
URL da la datoteca audio per l'outpainting.
extend_before_durationopziunal
Tipnumber
Standard0
0 – 107
Durada da l'extensiun avant il cumenzament da l'audio, en secundas.
extend_after_durationopziunal
Tipnumber
Standard30
0 – 107
Durada da l'extensiun suenter la fin da l'audio, en secundas.
tagsobligatori
Tipstring
Tags da stil audio furnids sco genres separads cun commas, cun `prompt` sco alternativa per als furnir.
lyricsopziunal
Tipstring
Standard
Text chantà, cun las parts da la chanzun organisadas cun controllas sco [verse], [chorus] e [bridge]. Per audio senza text chantà, ometta quest input u furnescha mo [inst] u [instrumental].
number_of_stepsopziunal
Tipinteger
Standard27
3 – 60
Dumber da pass utilisà durant la generaziun audio.
seedopziunal
Tipinteger | null
Seed per ina generaziun reproducibla, tschernì casualmain sche ti na furneschas nagina valur.
scheduleropziunal
Tipenum
Standardeuler
eulerheun
Scheduler utilisà durant la generaziun.
guidance_typeopziunal
Tipenum
Standardapg
cfgapgcfg_star
Tip CFG utilisà durant la generaziun.
granularity_scaleopziunal
Tipinteger
Standard10
-100 – 100
Scala da granularitad applitgada durant la generaziun. Augmentarla po reducir artifacts.
guidance_intervalopziunal
Tipnumber
Standard0.5
0 – 1
Part dal program da generaziun che survegn guida: la tscherna da 0.5 la restrenscha als pass da 0.25 * infer_steps fin a 0.75 * infer_steps, laschond l'inizial e la fin senza guida.
guidance_interval_decayopziunal
Tipnumber
Standard0
0 – 1
Decadiment da la guida entaifer l'interval da generaziun: 0.0 lascha il decadiment disactivà; autramain sa reducescha la scala durant quest interval da guidance_scale a min_guidance_scale.
guidance_scaleopziunal
Tipnumber
Standard15
0 – 200
Scala da la guida applitgada durant la generaziun.
minimum_guidance_scaleopziunal
Tipnumber
Standard3
0 – 200
Scala minimala da la guida cuntanschida suenter il decadiment durant la generaziun.
tag_guidance_scaleopziunal
Tipnumber
Standard5
0 – 10
Scala da la guida da tags applitgada durant la generaziun.
lyric_guidance_scaleopziunal
Tipnumber
Standard1.5
0 – 10
Scala da la guida dal text chantà applitgada durant la generaziun.
obligatori Num canonic, er acceptà

Ils parameters da datotecas acceptan ina URL publica https://, ina URI data: fin a 10 MB u il file_url d'ina chargiada. Datotecas

Output

GET /requests/req_8k2m4q7x1z9c3v5b6n0p2r4t
{
  "id": "req_8k2m4q7x1z9c3v5b6n0p2r4t",
  "object": "request",
  "model": "ace-step/audio-outpaint",
  "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": 6,
    "usd": "0.006",
    "charged": 6,
    "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"
  }
}
Tias datotecas, tia decisiunMintga outputs[].url è ina copia en nossa memorisaziun: conservada per adina (pajà per GB-mes) u 7 dis gratuitamain, tenor la configuraziun dal conto u ?storage=.
La medema structura per mintga modeltype, url, content_type, width, height e duration, tant per maletgs sco per video e audio. output è l'object da resultat dal model sez.
Champs da l'output
audio
object {url, content_type, file_name, file_size}Datoteca audio producida da la generaziun.
seed
integerSeed casual utilisà durant la generaziun.
tags
stringTags da gener durant la generaziun.
lyrics
stringText chantà applitgà durant la generaziun.

Dapli models: Text a musica

Per agents AI: questa pagina sco Markdown è disponibla sut https://doitong.com/rm/developers/models/ace-step/audio-outpaint.md. Tut ils models e las guidas: https://doitong.com/developers/llms.txt