Nemotron 3 Nano Omni Audio | AI Speech-to-Text API

{ "output": "The audio is a recording of a male speaker with a United States English accent. He says, 'When you use this model, congratulations, you are enjoying the super service that WaveSpeed AI provides'." }

NVIDIA Nemotron-3 Nano Omni Audio

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

Parameter	Required	Description
prompt	Yes	English text prompt sent to the model.
audio_url	Yes	URL of the audio to analyze.
system_prompt	No	Optional system prompt used to steer behavior, tone, or response style.
reasoning_mode	No	Reasoning mode: `no_think` (default) or `think`.
max_tokens	No	Maximum number of tokens to generate. Default: `1024`.
temperature	No	Sampling temperature. Lower values are more deterministic. Default: `0.7`.
top_p	No	Nucleus sampling probability mass. Default: `0.95`.

How to Use

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

Max Tokens	Cost
1000	$0.01
1024	$0.01024
2000	$0.02
4000	$0.04
8000	$0.08

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.

Nemotron 3 Nano Omni Audio API — Quick start

Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/nvidia/nemotron-3-nano-omni/audio with your input as JSON. The endpoint returns a prediction id; poll the prediction endpoint until status flips to completed, then read the output URL from data.outputs[0]. Examples for Nemotron 3 Nano Omni Audio below.

HTTP example

# Submit the prediction
curl -X POST "https://api.wavespeed.ai/api/v3/nvidia/nemotron-3-nano-omni/audio" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $WAVESPEED_API_KEY" \
  -d '{
    "prompt": "A cinematic shot of a city at sunset, soft golden light",
    "reasoning_mode": "no_think",
    "max_tokens": 1024,
    "temperature": 0.7,
    "top_p": 0.95,
    "enable_sync_mode": false
}'

# Response includes a prediction id. Poll for the result:
curl -X GET "https://api.wavespeed.ai/api/v3/predictions/{request_id}/result" \
  -H "Authorization: Bearer $WAVESPEED_API_KEY"

# When status is "completed", read the output from data.outputs[0].

Node.js example

// npm install wavespeed
const WaveSpeed = require('wavespeed');

const client = new WaveSpeed(); // reads WAVESPEED_API_KEY from env

const result = await client.run("nvidia/nemotron-3-nano-omni/audio", {
        "prompt": "A cinematic shot of a city at sunset, soft golden light",
        "reasoning_mode": "no_think",
        "max_tokens": 1024,
        "temperature": 0.7,
        "top_p": 0.95,
        "enable_sync_mode": false
});

console.log(result.outputs[0]); // → URL of the generated output

Python example

# pip install wavespeed
import wavespeed

output = wavespeed.run(
    "nvidia/nemotron-3-nano-omni/audio",
    {
    "prompt": "A cinematic shot of a city at sunset, soft golden light",
    "reasoning_mode": "no_think",
    "max_tokens": 1024,
    "temperature": 0.7,
    "top_p": 0.95,
    "enable_sync_mode": false
}
)

print(output["outputs"][0])  # → URL of the generated output

Nemotron 3 Nano Omni Audio API — Frequently asked questions

What is the Nemotron 3 Nano Omni Audio API?

Nemotron 3 Nano Omni Audio is a NVIDIA model for AI inference, exposed as a REST API on WaveSpeedAI. 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. You can call it programmatically or try it from the playground above.

How do I call the Nemotron 3 Nano Omni Audio API?

POST your input parameters to the model's REST endpoint (shown in the API tab of this playground) with your WaveSpeedAI API key in the Authorization header. Submission returns a prediction ID; poll the prediction endpoint until status flips to "completed", then read the output URL from the result. The playground generates a ready-to-paste code sample in Python, JavaScript, or cURL for whatever inputs you've set. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/nvidia/nvidia-nemotron-3-nano-omni-audio.

How much does Nemotron 3 Nano Omni Audio cost per run?

Nemotron 3 Nano Omni Audio starts at $0.010 per run. That figure is the base price — the final charge scales with the parameters you set in the form (output size, length, count, references, or whatever knobs this model exposes), so a higher-quality or larger output costs more than a minimal one. The exact cost for your current input is shown live next to the Generate button before you submit, and the actual per-call charge is recorded on the prediction afterwards.

What inputs does Nemotron 3 Nano Omni Audio accept?

Key inputs: `prompt`, `audio_url`, `enable_sync_mode`, `max_tokens`, `reasoning_mode`, `system_prompt`. The full JSON schema (types, defaults, allowed values) is rendered above the Generate button and mirrored in the API reference at https://wavespeed.ai/docs/docs-api/nvidia/nvidia-nemotron-3-nano-omni-audio.

How do I get started with the Nemotron 3 Nano Omni Audio API?

Sign up for a free WaveSpeedAI account to claim starter credits, copy your API key from /accesskey, then call the endpoint shown in the API tab of the playground. The playground also auto-generates a code sample in Python, JavaScript, or cURL for the parameters you've set.

Can I use Nemotron 3 Nano Omni Audio outputs commercially?

Commercial usage rights depend on the model's license, set by its provider (NVIDIA). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.

ExamplesView all

Related Models

README

NVIDIA Nemotron-3 Nano Omni Audio

Why Choose This?

Parameters

How to Use

Example Prompt

Pricing

Billing Rules

Best Use Cases

Pro Tips

Notes

Related Models

Nemotron 3 Nano Omni Audio API — Quick start

Nemotron 3 Nano Omni Audio API — Frequently asked questions