GET

/v1/schemas/fal/audio/nvidia%2Fnemotron-asr-multilingual%2Fasr

kind inputactivity audiohash 0e126edcextracted Jul 6, 2026version currentsource upstream spec ↗

Request body

3 properties · 1 required · 0 $defs
propertytypedescriptionconstraints
audio_url*stringURL of the audio file to transcribe.
languageenumTarget language for transcription (language-ID prompt). 'auto' lets the model detect the language.auto | en-US | en-GB | es-US | es-ES | de-DE · +35 more · default: "auto"
accelerationenumControls the speed/accuracy trade-off. 'none' = best accuracy (1.12s chunks), 'regular' = balanced (0.56s chunks), 'high' = faster (0.32s chunks), 'full' = fastest (0.08s chunks).none | regular | high | full · default: "regular"

Validate a payload

before you spend tokens
shell
$ curl -X POST https://modelschemas.com/v1/validate \
    -d '{"provider":"fal","endpointId":"nvidia/nemotron-asr-multilingual/asr","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}