Ruka hadi kwenye maudhui

Sam Audio · Separate

Unganisha

Kitambulisho cha modeli sam-audio/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/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",
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
  }'

# 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"

Faili kama mfano: $ 0.05 salio za API 50 · ≈ ₽ 5.27 faili zako hupimwa kabla ya kuendesha Iendeshe kwenye ukurasa huu

Pata ufunguo wa API
Meta Sauti 10–60 s #audio-to-audio#sam-audio

Hutenga sauti kutoka kwenye faili la sauti kwa kutumia maelezo ya maandishi, na kurejesha njia za sauti lengwa na mabaki

Meta · Data (JSON)

Tokeo lako la kwanza linaonekana hapa

Unda ombi hapa chini na uliendeshe kwa ufunguo wako wa API. Matokeo yanakiliwa kwenye hifadhi yetu, yakihifadhiwa milele au 7 siku bila malipo.

Unda ombi

Vidhibiti vinazalishwa kutoka kwenye schema ya modeli. Msimbo na bei husasishwa unapovibadilisha.

•inahitajika

Maelezo ya maandishi ya sauti inayolengwa kutengwa.

•inahitajika audio_url
Dondosha faili, au

URL ya faili la sauti kwa uchakataji; miundo inayotumika ni WAV, MP3 na FLAC.

chaguomsingi 1

Idadi ya wagombea wanaozalishwa kwa ajili ya kupanga.

Ya kina acceleration · output_format · max_chunk_duration · chunk_overlap · predict_spans
acceleration chaguomsingi balanced

Kiwango cha kuongeza kasi kinachotumika kwenye uchakataji.

output_format chaguomsingi wav

Umbizo la sauti iliyozalishwa.

chaguomsingi 60

Kikomo cha sauti kwa kila pasi, kinachopimwa kwa sekunde, ambacho kikizidi uchakataji hutumia vipande vinavyopishana vinavyounganishwa pamoja.

chaguomsingi 5

Urefu wa mwingiliano kati ya vipande, unaopimwa kwa sekunde, unaotumika kwa uunganishaji wa crossfade.

POST /run/sam-audio/separate?wait=20 makadirio → $ 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/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",
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
  }'

# 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"

Endesha ombi hili

Key yako inabaki kwenye kivinjari hiki: inatumwa kwa Doitong API pekee na kuhifadhiwa (localStorage) tu ukiweka tiki kwenye Kumbuka. Pata ufunguo wa API

Kuhusu Sam Audio · Separate

Ipe `audio_url` (WAV, MP3 au FLAC) na `prompt` inayotaja sauti ya kutolewa. Matokeo yana njia ya `target` yenye sauti iliyotengwa na njia ya `residual` yenye kila kitu kingine. Chaguo ni pamoja na `predict_spans`, hadi `reranking_candidates` 7, kiwango cha `acceleration`, kugawa sauti ndefu katika vipande (sekunde 10 hadi 60 kwa kila mchakato) na matokeo ya wav au mp3.

Vigezo

Tuma jina rasmi au jina asilia, si yote mawili. Majina rasmi

JinaAina ChaguomsingiInaruhusiwa Maelezo
audio_urlinahitajika audio
Ainaurl · audio
URL ya faili la sauti kwa uchakataji; miundo inayotumika ni WAV, MP3 na FLAC.
promptinahitajika
Ainastring
Maelezo ya maandishi ya sauti inayolengwa kutengwa.
predict_spanssi lazima
Ainaboolean
Chaguomsingifalse
Utabiri wa kiotomatiki wa vipindi vya muda vilivyo na sauti lengwa.
reranking_candidatessi lazima
Ainainteger
Chaguomsingi1
1 – 7
Idadi ya wagombea wanaozalishwa kwa ajili ya kupanga.
accelerationsi lazima
Ainaenum
Chaguomsingibalanced
fastbalancedquality
Kiwango cha kuongeza kasi kinachotumika kwenye uchakataji.
max_chunk_durationsi lazima
Ainanumber
Chaguomsingi60
10 – 60
Kikomo cha sauti kwa kila pasi, kinachopimwa kwa sekunde, ambacho kikizidi uchakataji hutumia vipande vinavyopishana vinavyounganishwa pamoja.
chunk_overlapsi lazima
Ainanumber
Chaguomsingi5
0 – 30
Urefu wa mwingiliano kati ya vipande, unaopimwa kwa sekunde, unaotumika kwa uunganishaji wa crossfade.
output_formatsi lazima
Ainaenum
Chaguomsingiwav
wavmp3
Umbizo la sauti iliyozalishwa.
inahitajika Jina rasmi, pia linakubalika

Vigezo vya faili vinakubali URL ya umma ya https://, data: URI ya hadi 10 MB, au file_url ya upakiaji. Faili

Tokeo

GET /requests/req_8k2m4q7x1z9c3v5b6n0p2r4t
{
  "id": "req_8k2m4q7x1z9c3v5b6n0p2r4t",
  "object": "request",
  "model": "sam-audio/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",
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
  },
  "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"
  }
}
Faili zako, chaguo lakoKila outputs[].url ni nakala kwenye hifadhi yetu: huhifadhiwa milele (hutozwa kwa GB kwa mwezi) au 7 siku bila malipo, kulingana na mpangilio wa akaunti yako au ?storage=.
Muundo uleule kwenye kila modelitype, url, content_type, width, height na duration, kwa picha, video na sauti. output ni kitu cha matokeo cha modeli yenyewe.
Sehemu za tokeo
target
object {url, content_type, file_name, file_size}Sauti lengwa iliyotolewa ikiwa imetengwa.
residual
object {url, content_type, file_name, file_size}Sauti iliyobaki kando na sauti lengwa.
duration
numberUrefu wa tokeo la sauti, unaopimwa kwa sekunde.
sample_rate
integerMarudio ya sampuli katika Hz kwa sauti ya tokeo.

Miundo zaidi: Sauti

Kwa mawakala wa AI: ukurasa huu katika Markdown unapatikana kwenye https://doitong.com/sw/developers/models/sam-audio/separate.md. Modeli na miongozo yote: https://doitong.com/developers/llms.txt