Saltar al cuntegna

Nemotron 3 Nano Omni · Audio

Integrar

ID dal model 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"

Fin a $0,622 per execuziun pajà tenor l'utilisaziun effectiva, il rest vegn restituì Lantschar sin questa pagina

Obtegna ina clav API
NVIDIA Discurrer a text #nemotron#nvidia#audio-to-text#audio-understanding

Responda prompts davart in clip audio (wav u mp3, fin a 50 minutas) e returna text

NVIDIA · Text

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.

•obligatori

Text furnì sco prompt dal model; sto esser en englais.

Guida facultativa dal model furnida sco prompt dal sistem, senza raschunament en ses controlls; utilisescha `reasoning_mode` per quai.

•obligatori audio_url
Trametta in datoteca u

URL d’ina sequenza audio per l’input da raschunament; accepta wav u mp3 cun ina durada da maximalmain 50 minutas.

standard 1024

Limita superiura dal dumber da tokens generads.

Avanzà reasoning_mode · temperature · top_p · enable_safety_checker
reasoning_mode standard no_think

Format da resposta: `think` cuntegna ina traccia explicita dal chain-of-thought avant la resposta finala. Per ina resposta directa senza questa traccia, utilisescha `no_think`.

standard 0.7

Temperatura utilisada per il sampling; valurs pli pitschnas rendan l’output pli deterministic.

standard 0.95

Massa da probabilitad utilisada per il nucleus sampling.

POST /run/nvidia/nemotron-3-nano-omni/audio?wait=20 calculaziun → $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"

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 Nemotron 3 Nano Omni · Audio

La varianta audio accepta in `audio_url` che mussa ad in clip wav u mp3 da fin a 50 minutas, ensemen cun in `prompt` da text, e returnescha ina resposta da text. Ella è adattada per incumbensas da transcripziun u dumondas e respostas davart il tun. `reasoning_mode` activa ina fastiza da ragiunament explicita, e `max_tokens` po cuntanscher 20,000. Ils prompts duain esser en englais.

Parameters

Invia u il num canonic u il num nativ, betg omaduas. Nums canonics

NumTip StandardPermess Descripziun
promptobligatori
Tipstring
Text furnì sco prompt dal model; sto esser en englais.
system_promptopziunal
Tipstring | null
Guida facultativa dal model furnida sco prompt dal sistem, senza raschunament en ses controlls; utilisescha `reasoning_mode` per quai.
reasoning_modeopziunal
Tipenum
Standardno_think
thinkno_think
Format da resposta: `think` cuntegna ina traccia explicita dal chain-of-thought avant la resposta finala. Per ina resposta directa senza questa traccia, utilisescha `no_think`.
max_tokensopziunal
Tipinteger
Standard1024
1 – 20 000
Limita superiura dal dumber da tokens generads.
temperatureopziunal
Tipnumber
Standard0.7
0 – 2
Temperatura utilisada per il sampling; valurs pli pitschnas rendan l’output pli deterministic.
top_popziunal
Tipnumber
Standard0.95
0 – 1
Massa da probabilitad utilisada per il nucleus sampling.
enable_safety_checkeropziunal
Tipboolean
Standardtrue
Controllescha sche la verificaziun da segirezza è activada.
audio_urlobligatori audio
Tipurl · audio
URL d’ina sequenza audio per l’input da raschunament; accepta wav u mp3 cun ina durada da maximalmain 50 minutas.
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": "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"
  }
}
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
output
stringText producì sco resposta.
finish_reason
stringMotiv per terminar la generaziun.
usage
object {input_tokens, output_tokens}Consum da tokens collià a la dumonda.

Dapli models: Discurrer a text

Per agents AI: questa pagina sco Markdown è disponibla sut https://doitong.com/rm/developers/models/nvidia/nemotron-3-nano-omni/audio.md. Tut ils models e las guidas: https://doitong.com/developers/llms.txt