Saltar al cuntegna

Sam Audio · Span Separate

Integrar

ID dal model sam-audio/span-separate
# 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/sam-audio/span-separate?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",
    "spans": [
      {
        "end": 10,
        "include": true,
        "start": 6
      }
    ]
  }'

# 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: $0,05 50 credits API · ≈ ₽5,27 tias datotecas vegnan mesiradas avant l'execuziun Lantschar sin questa pagina

Obtegna ina clav API
Meta Audio 10–60 s #audio-to-audio#sam-audio

Isolescha in tun d'in audio cun intervalls temporals inditgads da tai, cun in'indicaziun textuala facultativa

Meta · Datas (JSON)

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.

Agid per identifitgar il tun per extrair audio dal segment. Ina descripziun textuala dal tun d'isolaziun è recumandada, ma betg obligatorica.

•obligatori audio_url
Trametta in datoteca u

URL da la datoteca audio per l'elavuraziun.

standard 1

Dumber da candidats utilisà mo cun in prompt da text: vegnan generads e rangads tants candidats. La separaziun mo per segment ignorescha questa configuraziun.

•obligatori

Intervals temporals che cuntegnan il tun tschertgà d'isolaziun.

Avanzà acceleration · output_format · max_chunk_duration · chunk_overlap · use_sound_activity_ranking · trim_to_span
acceleration standard balanced

Nivel d'acceleraziun applitgà a l'elavuraziun.

output_format standard wav

Format per l'audio generà.

standard 60

Limita audio per pass, mesirada en secundas; sur questa vegnan utilisads tocs surpostads che vegnan maschadads ensemen.

standard 5

Lunghezza da la surposiziun tranter ils tocs, mesirada en secundas, utilisada per la mascha da crossfade.

POST /run/sam-audio/span-separate?wait=20 calculaziun → $0,05
# 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/sam-audio/span-separate?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",
    "spans": [
      {
        "end": 10,
        "include": true,
        "start": 6
      }
    ]
  }'

# 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 Sam Audio · Span Separate

Empè da sa basar mo sin text, transmettas `spans` che inditgeschan cura ch'il tun da mira cumpara en `audio_url`. `prompt` è facultativ, ma gida a identifitgar il tip da tun. `trim_to_span` po tagliar la sortida al sectur da l'intervall, e `use_sound_activity_ranking` permetta ina reclassificaziun senza prompt. Restituescha audio `target` e `residual` en wav u mp3.

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'elavuraziun.
promptopziunal
Tipstring | null
Agid per identifitgar il tun per extrair audio dal segment. Ina descripziun textuala dal tun d'isolaziun è recumandada, ma betg obligatorica.
spansobligatori
Tipobject[]
Intervals temporals che cuntegnan il tun tschertgà d'isolaziun.
spans[].startobligatori
Tipnumber
≥ 0
Timestamp d'inizi dal segment, mesirà en secundas.
spans[].endobligatori
Tipnumber
≥ 0
Timestamp da fin dal segment, mesirà en secundas.
spans[].includeopziunal
Tipboolean
Standardtrue
Inclusiun da tuns entaifer il segment: True als includa, entant che False als excluda.
reranking_candidatesopziunal
Tipinteger
Standard1
1 – 7
Dumber da candidats utilisà mo cun in prompt da text: vegnan generads e rangads tants candidats. La separaziun mo per segment ignorescha questa configuraziun.
accelerationopziunal
Tipenum
Standardbalanced
fastbalancedquality
Nivel d'acceleraziun applitgà a l'elavuraziun.
max_chunk_durationopziunal
Tipnumber
Standard60
10 – 60
Limita audio per pass, mesirada en secundas; sur questa vegnan utilisads tocs surpostads che vegnan maschadads ensemen.
chunk_overlapopziunal
Tipnumber
Standard5
0 – 30
Lunghezza da la surposiziun tranter ils tocs, mesirada en secundas, utilisada per la mascha da crossfade.
use_sound_activity_rankingopziunal
Tipboolean
Standardfalse
Opziun per rangar l'activitad sonora che pretenda reranking_candidates > 1 e permetta ina rerangaziun effectiva per la separaziun mo per segment senza prompt da text. Ils candidats vegnan valitads tenor quant bain lur regiuns detectadas senza tun s'accordan cun ils segments furnids.
trim_to_spanopziunal
Tipboolean
Standardfalse
Selecziun da la lunghezza d'output tranter il segment specifitgà sulet e l'audio cumplet. L'activaziun scursa a l'interval temporal dal segment; False mantegna la lunghezza cumpletta e isoleschia il tun tschertgà durant tut il temp.
output_formatopziunal
Tipenum
Standardwav
wavmp3
Format per l'audio generà.
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": "sam-audio/span-separate",
  "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": 50,
    "usd": "0.05",
    "charged": 50,
    "refunded": 0
  },
  "input": {
    "audio_url": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3",
    "spans": [
      {
        "end": 10,
        "include": true,
        "start": 6
      }
    ]
  },
  "output": {
    "target": {
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
      "content_type": "image/jpeg",
      "file_name": "0-output.jpeg",
      "file_size": 1843200
    },
    "residual": {
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
      "content_type": "image/jpeg",
      "file_name": "0-output.jpeg",
      "file_size": 1843200
    },
    "duration": 5,
    "sample_rate": 48000
  },
  "outputs": [
    {
      "type": "file",
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
      "content_type": "image/jpeg",
      "file_size": 1843200,
      "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
target
object {url, content_type, file_name, file_size}Tun tschertgà extratg isoladamain.
residual
object {url, content_type, file_name, file_size}Audio restà, abstrahà dal tun tschertgà.
duration
numberLunghezza da l'audio d'output, mesirada en secundas.
sample_rate
integerFrequenza da samplar en Hz per l'audio output.

Dapli models: Audio

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