Nvidia Nemotron 3 Nano Omni Audio

Nvidia Nemotron 3 Nano Omni Audio

Playground

NVIDIA Nemotron 3 Nano Omni is an open, efficient reasoning model for enterprise agentic workflows, built on a 30B A3B hybrid Transformer-Mamba MoE architecture. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

NVIDIA Nemotron-3 Nano Omni Audio is a multimodal audio-language model for understanding and analyzing audio content. Provide an audio URL and an English prompt, and the model generates a text response for tasks such as audio description, spoken-content understanding, sound event analysis, and structured audio question answering.

Why Choose This?

• Audio understanding with natural-language prompts Ask questions about an audio clip or request summaries, descriptions, and structured analysis in plain English.

• Broad audio reasoning Analyze spoken content, sound events, acoustic context, and overall scene characteristics from uploaded audio.

• Flexible response control Adjust max_tokens, temperature, and top_p to balance response length, determinism, and creativity.

• Optional system steering Use system_prompt to guide output style, structure, or task behavior for more controlled results.

• Reasoning mode options Choose between no_think and think depending on your preferred response mode and workflow.

• Production-ready API Suitable for audio analysis pipelines, multimodal assistants, content review systems, and automated media understanding workflows.

Parameters

How to Use

1. Provide your audio URL — upload or link the audio you want the model to analyze.
2. Write your prompt — ask the model to describe, summarize, explain, classify, or answer questions about the audio.
3. Add a system prompt (optional) — guide the response style, structure, or task framing.
4. Choose reasoning mode (optional) — use no_think or think depending on your workflow.
5. Set generation controls (optional) — adjust max_tokens, temperature, and top_p.
6. Submit — run the model and review the generated response.

Example Prompt

Describe this audio in detail, including the type of sounds present, any spoken content, the overall environment, and the likely context of the recording.

Pricing

Billed by configured max_tokens.

Billing Rules

• Pricing is based on the configured max_tokens value.
• Cost is $0.01 per 1,000 max tokens.
• Increasing max_tokens increases cost linearly.
• prompt, system_prompt, reasoning_mode, temperature, and top_p do not change pricing directly.

Best Use Cases

• Audio summarization — Generate concise or detailed summaries of spoken or environmental audio.
• Sound event analysis — Identify notable sounds, acoustic cues, and scene characteristics.
• Audio question answering — Ask targeted questions about what can be heard in an audio clip.
• Speech and dialogue understanding — Analyze spoken content, conversations, or narration in structured ways.
• Content review workflows — Inspect uploaded audio for categorization, moderation, or review tasks.
• Multimodal assistants — Add audio-aware understanding to internal tools, bots, and applications.

Pro Tips

• Write prompts in English for best compatibility.
• Be specific about the task, such as summarization, sound identification, transcript-style understanding, or focused question answering.
• Use system_prompt when you need a consistent output format, such as bullet summaries, labeled sections, or structured JSON-like responses.
• Keep temperature lower when you want more stable and deterministic answers.
• Increase max_tokens only when you need longer outputs, since pricing is tied to that value.
• Ask focused questions like “what sounds are present,” “what is being said,” or “what is the likely recording environment” for clearer results.

Notes

• Both prompt and audio_url are required.
• prompt must be written in English.
• Default settings include reasoning_mode = no_think, max_tokens = 1024, temperature = 0.7, and top_p = 0.95.
• Pricing depends on configured max_tokens, not on other generation settings.

Related Models

• NVIDIA Nemotron-3 Nano Omni Vision — Analyze images with the same Omni model family.
• NVIDIA Nemotron-3 Nano Omni Video — Analyze video content with temporal understanding.
• NVIDIA Nemotron-3 Nano Omni Text — Use the text-only variant for language generation and text-based tasks.

Authentication

For authentication details, please refer to the Authentication Guide.

API Endpoints

Submit Task & Query Result

set -euo pipefail

export WAVESPEED_API_KEY="your-api-key"

REQUEST_BODY=$(cat <<'JSON'
{
  "prompt": "A cinematic ocean wave at sunrise, highly detailed",
  "audio_url": "https://interactive-examples.mdn.mozilla.net/media/cc0-audio/t-rex-roar.mp3",
  "reasoning_mode": "no_think",
  "max_tokens": 1024,
  "temperature": 0.7,
  "top_p": 0.95
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/nvidia/nemotron-3-nano-omni/audio" \
  -H "Authorization: Bearer ${WAVESPEED_API_KEY}" \
  -H "Content-Type: application/json" \
  -d "${REQUEST_BODY}")

TASK=$(printf '%s' "${SUBMIT_RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "${TASK}" | jq -r '.id // empty')
if [ -z "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL=$(printf '%s' "${TASK}" | jq -r '.urls.get // empty')
if [ -z "${RESULT_URL}" ]; then RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"; fi

# 2. Poll until the prediction finishes.
while true; do
  RESPONSE=$(curl --silent --show-error --fail-with-body \
    "${RESULT_URL}" \
    -H "Authorization: Bearer ${WAVESPEED_API_KEY}")
  RESULT=$(printf '%s' "${RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
  STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')

  case "${STATUS}" in
    completed) printf '%s\n' "${RESULT}" | jq '.outputs'; break ;;
    failed|cancelled|timeout) printf '%s\n' "${RESULT}" | jq . >&2; exit 1 ;;
    created|processing) sleep 2 ;;
    *) printf 'Unexpected status: %s
' "${STATUS}" >&2; exit 1 ;;
  esac
done

Parameters

Task Submission Parameters

Request Parameters

Response Parameters

Result Request Parameters

Result Response Parameters