Nemotron 3 Nano Omni · Audio

Unganisha

Kitambulisho cha modeli 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"

const API = "https://api.doitong.ru/v1";
const headers = {
  "Authorization": "Bearer " + process.env.DOITONG_API_KEY,
  "Content-Type": "application/json",
};

// Run the model; wait up to 20 s for the finished result in the same call
let res = await fetch(API + "/run/nvidia/nemotron-3-nano-omni/audio?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "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"
  }),
});
let request = await res.json();
if (!res.ok) throw new Error(request.error.code + ": " + request.error.message);

// Not finished yet: long-poll until it is
while (request.status === "queued" || request.status === "running") {
  res = await fetch(API + "/requests/" + request.id + "?wait=20", { headers });
  request = await res.json();
}
if (request.status !== "succeeded") throw new Error(JSON.stringify(request.error));
console.log(request.outputs.map((o) => o.url), request.cost.credits + " API credits ($" + request.cost.usd + ")");

import os
import requests

API = "https://api.doitong.ru/v1"
headers = {"Authorization": "Bearer " + os.environ["DOITONG_API_KEY"]}

payload = {
    "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",
}

# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/nvidia/nemotron-3-nano-omni/audio", params={"wait": 20}, json=payload, headers=headers)
request = r.json()
if not r.ok:
    raise RuntimeError(request["error"]["code"] + ": " + request["error"]["message"])

# Not finished yet: long-poll until it is
while request["status"] in ("queued", "running"):
    request = requests.get(API + "/requests/" + request["id"], params={"wait": 20}, headers=headers).json()
if request["status"] != "succeeded":
    raise RuntimeError(request["error"])
print([o["url"] for o in request["outputs"]], request["cost"]["credits"], "API credits", "$" + request["cost"]["usd"])

# 1. Connect once (Claude Code; Cursor, VS Code, Claude Desktop: https://doitong.com/sw/developers/docs/mcp)
claude mcp add --transport http doitong-models https://api.doitong.ru/v1/mcp \
  --header "Authorization: Bearer $DOITONG_API_KEY"

# 2. Your agent calls the "run" tool with:
{
  "model_id": "nvidia/nemotron-3-nano-omni/audio",
  "input": {
    "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"
  }
}

Piga modeli ya Nemotron 3 Nano Omni · Audio (nvidia/nemotron-3-nano-omni/audio) kupitia Doitong API. Nyaraka za mawakala: https://doitong.com/sw/developers/models/nvidia/nemotron-3-nano-omni/audio.md

POST https://api.doitong.ru/v1/run/nvidia/nemotron-3-nano-omni/audio?wait=20
Authorization: Bearer $DOITONG_API_KEY
Content-Type: application/json

{
  "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"
}

Ikiwa hali ya jibu ni "queued" au "running", piga GET https://api.doitong.ru/v1/requests/REQUEST_ID?wait=20 mara kwa mara hadi iwe "succeeded"; faili ziko kwenye outputs[].url. POST https://api.doitong.ru/v1/quote/nvidia/nemotron-3-nano-omni/audio yenye mwili uleule hurejesha bei kamili kabla ya kuendesha.

Hadi $ 0.622 kwa kila uendeshaji hutozwa kulingana na matumizi halisi, yaliyosalia yanarejeshwa Iendeshe kwenye ukurasa huu

Pata ufunguo wa API

NVIDIA Matamshi hadi Maandishi #nemotron#nvidia#audio-to-text#audio-understanding

Hujibu vidokezo kuhusu klipu ya sauti (wav au mp3, hadi dakika 50) na kurudisha maandishi

OpenAPI Markdown

NVIDIA · Maandishi

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.

prompt •inahitajika

Maandishi yaliyotolewa kama kidokezo cha modeli; lazima yawe kwa Kiingereza.

system_prompt

Mwongozo wa hiari wa modeli uliotolewa kama kidokezo cha mfumo, huku hoja zikitengwa na vidhibiti vyake; tumia `reasoning_mode` badala yake.

audio •inahitajika audio_url

Dondosha faili, au

URL ya klipu ya sauti kwa ingizo la hoja; inakubali wav au mp3 yenye muda usiozidi dakika 50.

max_tokens chaguomsingi 1024

Kikomo cha juu cha tokeni zinazozalishwa.

Ya kina reasoning_mode · temperature · top_p · enable_safety_checker

reasoning_mode chaguomsingi no_think

Umbizo la jibu: `think` hujumuisha mfululizo wa wazi wa hoja kabla ya kuwasilisha jibu la mwisho. Kwa jibu la moja kwa moja bila mfululizo huo, tumia `no_think`.

temperature chaguomsingi 0.7

Joto linalotumika kwa sampuli; thamani ndogo hufanya tokeo liwe la kubashirika zaidi.

top_p chaguomsingi 0.95

Mkusanyiko wa uwezekano unaotumika kwa sampuli ya kiini.

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

const API = "https://api.doitong.ru/v1";
const headers = {
  "Authorization": "Bearer " + process.env.DOITONG_API_KEY,
  "Content-Type": "application/json",
};

// Run the model; wait up to 20 s for the finished result in the same call
let res = await fetch(API + "/run/nvidia/nemotron-3-nano-omni/audio?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "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"
  }),
});
let request = await res.json();
if (!res.ok) throw new Error(request.error.code + ": " + request.error.message);

// Not finished yet: long-poll until it is
while (request.status === "queued" || request.status === "running") {
  res = await fetch(API + "/requests/" + request.id + "?wait=20", { headers });
  request = await res.json();
}
if (request.status !== "succeeded") throw new Error(JSON.stringify(request.error));
console.log(request.outputs.map((o) => o.url), request.cost.credits + " API credits ($" + request.cost.usd + ")");

import os
import requests

API = "https://api.doitong.ru/v1"
headers = {"Authorization": "Bearer " + os.environ["DOITONG_API_KEY"]}

payload = {
    "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",
}

# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/nvidia/nemotron-3-nano-omni/audio", params={"wait": 20}, json=payload, headers=headers)
request = r.json()
if not r.ok:
    raise RuntimeError(request["error"]["code"] + ": " + request["error"]["message"])

# Not finished yet: long-poll until it is
while request["status"] in ("queued", "running"):
    request = requests.get(API + "/requests/" + request["id"], params={"wait": 20}, headers=headers).json()
if request["status"] != "succeeded":
    raise RuntimeError(request["error"])
print([o["url"] for o in request["outputs"]], request["cost"]["credits"], "API credits", "$" + request["cost"]["usd"])

{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "run",
    "arguments": {
      "model_id": "nvidia/nemotron-3-nano-omni/audio",
      "input": {
        "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"
      },
      "wait_seconds": 20
    }
  }
}

Endesha ombi hili

Ufunguo wa API

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

Kuhusu Nemotron 3 Nano Omni · Audio

Toleo la sauti hupokea `audio_url` inayoelekeza kwenye klipu ya wav au mp3 yenye hadi dakika 50, pamoja na `prompt` ya maandishi, na kurudisha jibu la maandishi. Linafaa kwa kazi za unukuzi au kujibu maswali kuhusu sauti. `reasoning_mode` huwasha au kuzima mfululizo wa hoja, na `max_tokens` inaweza kufikia 20,000. Vidokezo vinapaswa kuwa kwa Kiingereza.

Vigezo

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

JinaAina ChaguomsingiInaruhusiwa Maelezo

promptinahitajika

Ainastring

Maandishi yaliyotolewa kama kidokezo cha modeli; lazima yawe kwa Kiingereza.

system_promptsi lazima

Ainastring | null

Mwongozo wa hiari wa modeli uliotolewa kama kidokezo cha mfumo, huku hoja zikitengwa na vidhibiti vyake; tumia `reasoning_mode` badala yake.

reasoning_modesi lazima

Ainaenum

Chaguomsingino_think

thinkno_think

Umbizo la jibu: `think` hujumuisha mfululizo wa wazi wa hoja kabla ya kuwasilisha jibu la mwisho. Kwa jibu la moja kwa moja bila mfululizo huo, tumia `no_think`.

max_tokenssi lazima

Ainainteger

Chaguomsingi1024

1 – 20,000

Kikomo cha juu cha tokeni zinazozalishwa.

temperaturesi lazima

Ainanumber

Chaguomsingi0.7

0 – 2

Joto linalotumika kwa sampuli; thamani ndogo hufanya tokeo liwe la kubashirika zaidi.

top_psi lazima

Ainanumber

Chaguomsingi0.95

0 – 1

Mkusanyiko wa uwezekano unaotumika kwa sampuli ya kiini.

enable_safety_checkersi lazima

Ainaboolean

Chaguomsingitrue

Hudhibiti ikiwa ukaguzi wa usalama umewashwa.

audio_urlinahitajika audio

Ainaurl · audio

URL ya klipu ya sauti kwa ingizo la hoja; inakubali wav au mp3 yenye muda usiozidi dakika 50.

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": "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"
  }
}

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

output: stringMaandishi yaliyotolewa kama jibu.
finish_reason: stringSababu ya kumaliza uzalishaji.
usage: object {input_tokens, output_tokens}Matumizi ya tokeni yanayohusishwa na ombi.

Miundo zaidi: Matamshi hadi Maandishi

Kwa mawakala wa AI: ukurasa huu katika Markdown unapatikana kwenye https://doitong.com/sw/developers/models/nvidia/nemotron-3-nano-omni/audio.md. Modeli na miongozo yote: https://doitong.com/developers/llms.txt

Tokeo lako la kwanza linaonekana hapa

Unda ombi

Endesha ombi hili

Kuhusu Nemotron 3 Nano Omni · Audio

Vigezo

Tokeo

Tofauti nyingine za Nemotron 3 Nano Omni

Nemotron 3 Nano Omni Tofauti: 4

Nemotron 3 Nano Omni · Video Tofauti: 4

Nemotron 3 Nano Omni · Vision Tofauti: 4

Miundo zaidi: Matamshi hadi Maandishi

Nemotron Asr Multilingual

Cohere Transcribe

Elevenlabs - Forced Alignment Tofauti: 4

ElevenLabs Speech to Text Tofauti: 2