Peke ki ngā ihirangi

Sam Audio · Span Separate

Whakauru

id tauira 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.com/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.com/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"

Ngā kōnae pēnei i te tauira: $ 0.05 50 whiwhinga API ka inea ō kōnae i mua i te whakahaere Whakahaerehia ki tēnei whārangi

Tikina he kī API
Meta Ororongo 10–60 s #audio-to-audio#sam-audio

Ka wehea he oro mai i te ororongo mā ngā awhe wā ka hoatu e koe, me tētahi tohu kuputuhi kōwhiringa

Meta · Raraunga (JSON)

Kei konei tō hua tuatahi

Hangaia he tono ki raro nei, ka whakahaere mā tō kī API. Ka tāruatia ngā putanga ki tō mātou rokiroki, ka puritia mō ake tonu atu, mō rānei 7 rā mō te kore utu.

Hangaia he tono

Ka hangaia ngā mana whakahaere mai i te aronuinga o te tauira. Ka whakahoungia te waehere me te utu ina whakarerekē koe.

Āwhina tautuhi oro mō te tango ororongo mai i te wāhanga. E taunakitia ana he whakaahuatanga kuputuhi mō te oro hei wehe, engari ehara i te mea here.

•e hiahiatia ana audio_url
Whakataka he kōnae,

URL kōnae ororongo mō te tukatuka.

taunoa 1

Te maha o ngā kaitono, ka whakamahia me te tohutohu kuputuhi anake: ka whakaputaina, ka whakaraupapatia taua maha o ngā kaitono. Ka waiho tēnei tautuhinga ki te wehewehenga wāhanga anake.

•e hiahiatia ana

Ngā wā kei roto te oro whāia hei wehe.

Arā atu acceleration · output_format · max_chunk_duration · chunk_overlap · use_sound_activity_ranking · trim_to_span
acceleration taunoa balanced

Taumata whakatere i whakamahia mō te tukatuka.

output_format taunoa wav

Hōputu mō te ororongo kua whakaputaina.

taunoa 60

Te rohe ororongo mō ia tukunga, hei hēkona; ki tua atu, ka whakamahi te tukatuka i ngā wāhanga inaki ka hanumihia.

taunoa 5

Te roa o te inaki i waenga i ngā wāhanga, hei hēkona, mō te hanumi whakawhiti.

POST /run/sam-audio/span-separate?wait=20 utu → $ 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/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.com/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"

Whakahaerehia tēnei tono

Ka noho tō kī ki tēnei pūtirotiro: ka tukuna ki te Doitong API anake, ā, ka tiakina ki te localStorage anake ina tohua e koe te Mahara. Tikina he kī API

Mō Sam Audio · Span Separate

Kāore e whakawhirinaki ki te kuputuhi anake; tukuna ngā `spans` e tohu ana i te wā ka puta te oro whāia i roto i `audio_url`. He kōwhiringa te `prompt`, engari ka āwhina ki te tautuhi i te momo oro. Ka taea e `trim_to_span` te tapahi i te putanga ki te awhe span, ā, mā `use_sound_activity_ranking` e taea ai te whakaraupapa anō me te kore tohutohu. Ka whakahoki ororongo `target` me `residual` i te wav, i te mp3 rānei.

Ngā tawhā

Tukuna te ingoa tōmua, te ingoa taketake rānei, kaua e rua. Ngā ingoa tōmua

IngoaMomo TaunoaE whakaaetia ana Whakamārama
audio_urle hiahiatia ana audio
Momourl · audio
URL kōnae ororongo mō te tukatuka.
promptkōwhiringa
Momostring | null
Āwhina tautuhi oro mō te tango ororongo mai i te wāhanga. E taunakitia ana he whakaahuatanga kuputuhi mō te oro hei wehe, engari ehara i te mea here.
spanse hiahiatia ana
Momoobject[]
Ngā wā kei roto te oro whāia hei wehe.
spans[].starte hiahiatia ana
Momonumber
≥ 0
Tīmātā wā tīmatanga o te wāhanga, hei hēkona.
spans[].ende hiahiatia ana
Momonumber
≥ 0
Tīmātā wā mutunga o te wāhanga, hei hēkona.
spans[].includekōwhiringa
Momoboolean
Taunoatrue
Te whakauru i ngā oro kei roto i te wāhanga: ka whakaurua e True, ka whakakorehia e False.
reranking_candidateskōwhiringa
Momointeger
Taunoa1
1 – 7
Te maha o ngā kaitono, ka whakamahia me te tohutohu kuputuhi anake: ka whakaputaina, ka whakaraupapatia taua maha o ngā kaitono. Ka waiho tēnei tautuhinga ki te wehewehenga wāhanga anake.
accelerationkōwhiringa
Momoenum
Taunoabalanced
fastbalancedquality
Taumata whakatere i whakamahia mō te tukatuka.
max_chunk_durationkōwhiringa
Momonumber
Taunoa60
10 – 60
Te rohe ororongo mō ia tukunga, hei hēkona; ki tua atu, ka whakamahi te tukatuka i ngā wāhanga inaki ka hanumihia.
chunk_overlapkōwhiringa
Momonumber
Taunoa5
0 – 30
Te roa o te inaki i waenga i ngā wāhanga, hei hēkona, mō te hanumi whakawhiti.
use_sound_activity_rankingkōwhiringa
Momoboolean
Taunoafalse
Kōwhiringa whakaraupapa ngohe oro me nui ake te reranking_candidates i te 1, kia whaihua ai te whakaraupapa anō mō te wehewehenga wāhanga anake, kāore he tohutohu kuputuhi. Ka whakatauria ngā kaitono e te tata o te hāngaitanga o ō rātou rohe kore-puku kua kitea ki ngā wāhanga kua tukuna.
trim_to_spankōwhiringa
Momoboolean
Taunoafalse
Kōwhiringa roa putanga i waenga i te wāhanga kua tohua me te ororongo katoa. Mā te whakahohe ka poroa ki te awhe wā o te wāhanga; mā False ka pupuri i te roa katoa, ka wehe i te oro whāia puta noa.
output_formatkōwhiringa
Momoenum
Taunoawav
wavmp3
Hōputu mō te ororongo kua whakaputaina.
e hiahiatia ana Ingoa tōmua, e whakaaetia ana hoki

Mō ngā tawhā kōnae, whakamahia he URL tūmatanui https://, he URI data: tae atu ki te 10 MB, he file_url rānei o tētahi tukuake. Ngā kōnae

Putanga

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.com/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
    "cancel": "https://api.doitong.com/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t/cancel"
  }
}
Ō kōnae, māu e whiriwhiriKo ia url o outputs[] he tārua kei tō mātou rokiroki: ka puritia mō ake tonu atu (ka utua ia GB-marama) mō rānei 7 rā mō te kore utu, e ai ki ngā tautuhinga o tō pūkete, ki te ?storage= rānei.
He ōrite te hanga ki ia tauiratype, url, content_type, width, height me duration, mō ngā pikitia, ataata me te oro. Ko output te ahanoa hua ake o te tauira.
Ngā āpure o te putanga
target
object {url, content_type, file_name, file_size}Te oro whāia kua tangohia motuhake.
residual
object {url, content_type, file_name, file_size}Te ororongo e toe ana i tua atu i te oro whāia.
duration
numberTe roa o te ororongo putanga, hei hēkona.
sample_rate
integerAuautanga tauira i roto i te Hz mō te ororongo putanga.

Ētahi atu tauira: Ororongo

Mō ngā āpiha AI: kei te wātea tēnei whārangi hei Markdown ki https://doitong.com/mi/developers/models/sam-audio/span-separate.md. Ngā tauira me ngā aratohu katoa: https://doitong.com/developers/llms.txt