Dža ko lil

Sam Audio · Visual Separate

Integriruj

Modelosko id sam-audio/visual-separate
# 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/sam-audio/visual-separate?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "video": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4"
  }'

# 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: $0.05 50 API krediti tire fajlo si merime angl-o phiripen Phir les kate

Lel API klidin
Meta Video ko Audio 10–60 s #video-to-audio#sam-audio

Separuil jek zvuko katar videonqo audio-track, opcionalone mask-video thaj tekstune prompt-eha

Meta · Dada (JSON)

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.

standardno

Natural-language deskripcija e targetoske zvukoski vaško separacija.

•trubul video_url
Čhiv jekh fajl, vaj

Video fajlosko URL vaško obrabotka, formatonθe sar MP4 vaj MOV.

standardno 1

Gin kandidaton save kerde pes vaško rangiripe.

Lučhe mask_video_url · acceleration · output_format · max_chunk_duration · chunk_overlap
Čhiv jekh fajl, vaj

Maskako video URL binary encoding-esa, kaj o targetosko objekto si kalo upral parno fondo.

acceleration standardno balanced

Acceleration level aplicado ko processing.

output_format standardno wav

Formato pala kerde audio.

standardno 60

Audio limit sako passosko, sikavdo sekundaθe; upral leste obrabotka užil overlapping chunkora save blendinen pes jekhetane.

standardno 5

Lungipe e overlap-ako maškar chunkora, sikavdo sekundaθe, užito vaško crossfade blending.

POST /run/sam-audio/visual-separate?wait=20 hesab → $0.05
# 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/sam-audio/visual-separate?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "video": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4"
  }'

# 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 Sam Audio · Visual Separate

Lel `video_url` thaj ekstraktuinel target-zvukos andar leskoro audio. Optionalno `mask_video_url` sikavel o target-objekto (kalo targetoske, parno backgroundoske), thaj `prompt` šaj te del tekstosko hint. Dži 4 `reranking_candidates` šaj te aven rank-ime, thaj lungo audio si chunk-ime. O rezultato si `target` thaj `residual` audio wav vaj mp3.

Parametra

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

NavTip standardnoMuklo Vakeripe
video_urltrubul video
Tipurl · video
Video fajlosko URL vaško obrabotka, formatonθe sar MP4 vaj MOV.
mask_video_urlopcionalno
Tipurl · video
Maskako video URL binary encoding-esa, kaj o targetosko objekto si kalo upral parno fondo.
promptopcionalno
Tipstring
standardno
Natural-language deskripcija e targetoske zvukoski vaško separacija.
reranking_candidatesopcionalno
Tipinteger
standardno1
1 – 4
Gin kandidaton save kerde pes vaško rangiripe.
accelerationopcionalno
Tipenum
standardnobalanced
fastbalancedquality
Acceleration level aplicado ko processing.
max_chunk_durationopcionalno
Tipnumber
standardno60
10 – 60
Audio limit sako passosko, sikavdo sekundaθe; upral leste obrabotka užil overlapping chunkora save blendinen pes jekhetane.
chunk_overlapopcionalno
Tipnumber
standardno5
0 – 30
Lungipe e overlap-ako maškar chunkora, sikavdo sekundaθe, užito vaško crossfade blending.
output_formatopcionalno
Tipenum
standardnowav
wavmp3
Formato pala kerde audio.
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": "sam-audio/visual-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": {
    "video_url": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4"
  },
  "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.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
target
object {url, content_type, file_name, file_size}Targetosko zvuko ekstraktirimo izolacijate.
residual
object {url, content_type, file_name, file_size}Audio savo ačhol avrial targetosko zvukostar.
duration
numberRezultato audiosko lungipe, sikavdo sekundaθe.
sample_rate
integerSampling frekvencija ande Hz pala rezultato audio.

Bute modeli: Video ko Audio

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