Peke ki ngā ihirangi

Nemotron 3 Nano Omni · Audio

Whakauru

id tauira nvidia/nemotron-3-nano-omni/audio
# 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/nvidia/nemotron-3-nano-omni/audio?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "audio": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3"
  }'

# 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"

Tae atu ki te $ 0.622 mō ia whakahaerenga ka utua mō te whakamahinga tūturu, ka whakahokia te toenga Whakahaerehia ki tēnei whārangi

Tikina he kī API
NVIDIA Kōrero ki te Kuputuhi #nemotron#nvidia#audio-to-text#audio-understanding

Ka whakautu i ngā tono mō tētahi topenga ororongo (wav, mp3 rānei, tae atu ki te 50 meneti), ka whakahoki kuputuhi

NVIDIA · Kuputuhi

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.

•e hiahiatia ana

Te tuhinga i tukuna hei tohutohu mō te tauira; me reo Ingarihi.

Te arataki tauira kōwhiringa i tukuna hei tohutohu pūnaha, kāore e whai wāhi ana te whakaaro ki ōna whakahaere; whakamahia `reasoning_mode` mō tērā.

•e hiahiatia ana audio_url
Whakataka he kōnae,

Te URL topenga ororongo mō te tāuru whakaaro; ka whakaaetia wav, mp3 rānei, kaua e roa ake i te 50 meneti.

taunoa 1024

Te rohe runga mō ngā tohu kua whakaputaina.

Arā atu reasoning_mode · temperature · top_p · enable_safety_checker
reasoning_mode taunoa no_think

Hōputu whakautu: kei roto i `think` tētahi ara whakaaro mārama i mua i te whakaatu i te whakautu whakamutunga. Mō te whakautu tika kāore taua ara, whakamahia `no_think`.

taunoa 0.7

Te pāmahana mō te tīpako; mā ngā uara iti ake ka tino matapae ake te putanga.

taunoa 0.95

Te papatipu tūponotanga mō te tīpako nucleus.

POST /run/nvidia/nemotron-3-nano-omni/audio?wait=20 utu → $ 0.622
# 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/nvidia/nemotron-3-nano-omni/audio?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "audio": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3"
  }'

# 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"

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 Nemotron 3 Nano Omni · Audio

Ka tango te momo ororongo i tētahi `audio_url` e tohu ana ki tētahi topenga wav, mp3 rānei tae atu ki te 50 meneti, me tētahi `prompt` kuputuhi, ka whakahoki whakautu kuputuhi. He pai mō ngā mahi momo tuhinga kōrero, pātai-whakautu rānei mō te oro. Mā `reasoning_mode` e whakawhiti i tētahi ara whakaaro mārama, ā, ka tae `max_tokens` ki 20,000. Me reo Ingarihi ngā tono.

Ngā tawhā

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

IngoaMomo TaunoaE whakaaetia ana Whakamārama
prompte hiahiatia ana
Momostring
Te tuhinga i tukuna hei tohutohu mō te tauira; me reo Ingarihi.
system_promptkōwhiringa
Momostring | null
Te arataki tauira kōwhiringa i tukuna hei tohutohu pūnaha, kāore e whai wāhi ana te whakaaro ki ōna whakahaere; whakamahia `reasoning_mode` mō tērā.
reasoning_modekōwhiringa
Momoenum
Taunoano_think
thinkno_think
Hōputu whakautu: kei roto i `think` tētahi ara whakaaro mārama i mua i te whakaatu i te whakautu whakamutunga. Mō te whakautu tika kāore taua ara, whakamahia `no_think`.
max_tokenskōwhiringa
Momointeger
Taunoa1024
1 – 20,000
Te rohe runga mō ngā tohu kua whakaputaina.
temperaturekōwhiringa
Momonumber
Taunoa0.7
0 – 2
Te pāmahana mō te tīpako; mā ngā uara iti ake ka tino matapae ake te putanga.
top_pkōwhiringa
Momonumber
Taunoa0.95
0 – 1
Te papatipu tūponotanga mō te tīpako nucleus.
enable_safety_checkerkōwhiringa
Momoboolean
Taunoatrue
Ka whakahaere mēnā kua whakakāhia te tirotiro haumaru.
audio_urle hiahiatia ana audio
Momourl · audio
Te URL topenga ororongo mō te tāuru whakaaro; ka whakaaetia wav, mp3 rānei, kaua e roa ake i te 50 meneti.
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": "nvidia/nemotron-3-nano-omni/audio",
  "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": 622,
    "usd": "0.622",
    "charged": 622,
    "refunded": 0
  },
  "input": {
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "audio_url": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3"
  },
  "output": {
    "output": "The image shows a golden retriever puppy sitting on a wooden floor.",
    "finish_reason": "stop",
    "usage": {
      "input_tokens": 1,
      "output_tokens": 1
    }
  },
  "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"
  }
}
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
output
stringTe tuhinga i whakaputaina hei whakautu.
finish_reason
stringTe take i mutu ai te whakaputanga.
usage
object {input_tokens, output_tokens}Te whakamahinga tohu e pā ana ki te tono.

Ētahi atu tauira: Kōrero ki te Kuputuhi

Mō ngā āpiha AI: kei te wātea tēnei whārangi hei Markdown ki https://doitong.com/mi/developers/models/nvidia/nemotron-3-nano-omni/audio.md. Ngā tauira me ngā aratohu katoa: https://doitong.com/developers/llms.txt