falSpeech to textComing soon

nvidia/nemotron-3-nano-omni/audio

Name: nvidia/nemotron-3-nano-omni/audio
Brand: fal

nvidia/nemotron-3-nano-omni/audio is a speech to text tool from fal that runs in the background and returns structured JSON. Coming soon: listed with its price, not yet open to runs.

This tool is listed but not yet available to run.

Price pending

Pricing

Price pending.

Limits

Runs: In the background
Returns: json
Longest queue wait: 3600s
Run deadline: 1800s
Largest inline input: 1024 KB
Largest input file: 500 MB
Largest output: 4768 MB
Outputs per run: 16

Input

Field	Kind	Default	Description
`prompt` required	text	—	Text prompt to send to the model. English only.
`system_prompt`	text	—	Optional system prompt to steer the model. Reasoning behavior is controlled by the separate `reasoning_mode` field.
`reasoning_mode`	one of think, no_think	no_think	Whether the model should emit an explicit reasoning trace. `no_think` returns a direct answer; `think` returns chain-of-thought followed by the final answer.
`max_tokens`	number (whole) 1 to 20000	1024	Maximum number of tokens to generate.
`temperature`	number 0 to 2	0.7	Sampling temperature. Lower is more deterministic.
`top_p`	number 0 to 1	0.95	Nucleus sampling probability mass.
`audio_url` required	URL or file	—	URL of the audio clip to reason about. wav or mp3, max 50 minutes.

Same request in code

curl https://api.spiral.ai/v1/runs \
  -H "Authorization: Bearer $SPIRAL_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
    "provider": "fal",
    "model": "nvidia/nemotron-3-nano-omni/audio",
    "input": {
      "prompt": "Summarize the key capabilities of a multimodal agent.",
      "audio_url": "https://storage.googleapis.com/falserverless/example_inputs/nemotron-3-nano-omni/audio_in.mp3"
    }
  }'