infery
← All models

Nemotron Asr Multilingual

nemotron-asr-multilingual-asr

Speech to Textby NVIDIA

Nemotron-ASR-Streaming is a multi lingual, streaming Automatic Speech Recognition (ASR) engineered to deliver high-quality multi lingual transcription across both low-latency streaming and high-throughput batch workloads.

Details

Accepts
audio

Pricing

Price
1 cr / minute

Prices in credits (1 credit = $0.01).

Data schema

Input

FieldTypeDescription
languagestringenum: auto, en-US, en-GB, es-US, es-ES, de-DETarget language for transcription (language-ID prompt). 'auto' lets the model detect the language.
audio_urlrequiredstringURL of the audio file to transcribe.
accelerationstringenum: none, regular, high, fullControls 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).

Output

FieldTypeDescription
outputstringThe transcribed text from the audio.
partialbooleanTrue if this is an intermediate result during streaming.