Skip to content

Nemotron 3 Nano Omni · Audio

Integrate

Model id 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"

Up to $0.622 per run charged by actual usage, the rest is refunded Run it on this page

Get API key
NVIDIA Speech to Text #nemotron#nvidia#audio-to-text#audio-understanding

Answers prompts about an audio clip (wav or mp3, up to 50 minutes), returning text

NVIDIA · Text

Your first result goes here

Build a request below and run it with your API key. Outputs are copied to our storage, kept forever or 7 days for free.

Build a request

Controls are generated from the model schema. The code and the price update as you change them.

•required

Text supplied as the model's prompt; must be in English.

Optional model guidance supplied as a system prompt, with reasoning excluded from its controls; use `reasoning_mode` for that instead.

•required audio_url
Drop a file, or

Audio clip URL for reasoning input; accepts wav or mp3 with a duration no longer than 50 minutes.

default 1024

Upper limit on generated tokens.

Advanced reasoning_mode · temperature · top_p · enable_safety_checker
reasoning_mode default no_think

Answer format: `think` includes an explicit chain-of-thought trace before presenting the final answer. For a direct answer without that trace, use `no_think`.

default 0.7

Temperature used for sampling; smaller values make output more deterministic.

default 0.95

Probability mass used for nucleus sampling.

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

Run this request

Your key stays in this browser: it is sent only to the Doitong API and saved (localStorage) only if you tick Remember. Get an API key

About Nemotron 3 Nano Omni · Audio

The audio variant takes an `audio_url` pointing to a wav or mp3 clip of up to 50 minutes, plus a text `prompt`, and returns a text response. It suits transcription-style or question-answering tasks about the sound. `reasoning_mode` toggles an explicit reasoning trace, and `max_tokens` can reach 20,000. Prompts should be in English.

Parameters

Send either the canonical name or the native name, not both. Canonical names

NameType DefaultAllowed Description
promptrequired
Typestring
Text supplied as the model's prompt; must be in English.
system_promptoptional
Typestring | null
Optional model guidance supplied as a system prompt, with reasoning excluded from its controls; use `reasoning_mode` for that instead.
reasoning_modeoptional
Typeenum
Defaultno_think
thinkno_think
Answer format: `think` includes an explicit chain-of-thought trace before presenting the final answer. For a direct answer without that trace, use `no_think`.
max_tokensoptional
Typeinteger
Default1024
1 – 20,000
Upper limit on generated tokens.
temperatureoptional
Typenumber
Default0.7
0 – 2
Temperature used for sampling; smaller values make output more deterministic.
top_poptional
Typenumber
Default0.95
0 – 1
Probability mass used for nucleus sampling.
enable_safety_checkeroptional
Typeboolean
Defaulttrue
Controls whether safety checking is enabled.
audio_urlrequired audio
Typeurl · audio
Audio clip URL for reasoning input; accepts wav or mp3 with a duration no longer than 50 minutes.
required Canonical name, also accepted

File parameters take a public https:// URL, a data: URI up to 10 MB, or the file_url of an upload. Files

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"
  }
}
Your files, your choiceEvery outputs[].url is a copy on our storage: kept forever (paid per GB-month) or 7 days for free, by your account setting or ?storage=.
Same shape on every modeltype, url, content_type, width, height and duration, for images, video and audio alike. output is the model’s own result object.
Fields of output
output
stringText produced as the response.
finish_reason
stringReason for ending generation.
usage
object {input_tokens, output_tokens}Token consumption associated with the request.

More models: Speech to Text

For AI agents: this page as Markdown is at https://doitong.com/en-US/developers/models/nvidia/nemotron-3-nano-omni/audio.md. All models and guides: https://doitong.com/developers/llms.txt