NVIDIA: Nemotron 3.5 ASR Streaming Multilingual 0.6B

Origin

nvidia/nemotron-3.5-asr-streaming-multilingual-0.6b

Nemotron 3.5 ASR Streaming Multilingual 0.6B is a speech recognition model from NVIDIA. Its prompt-conditioned, cache-aware FastConformer-RNNT design targets low-latency transcription across more than 40 languages for real-time captioning, voice...

Pricing

Billed at actual usage

Billing follows the provider's own reported cost. The unit prices here are for reference; a model marked "billed at actual usage" has no reliable pre-call price, so your usage page is the record of what you paid.

Capabilities

Audio

Call it

Transcription is served on POST /v1/audio/transcriptions and takes a multipart file upload. **The format is inferred from the filename extension**, so the file must have one (mp3, wav, m4a, flac, ogg, webm, …). response_format supports json, verbose_json and text; srt and vtt are not supported in this release. Uploads are capped at 36 MiB.

curl https://macdecloud.com/v1/audio/transcriptions \
  -H "Authorization: Bearer dcld-sk-..." \
  -F file=@meeting.mp3 \
  -F model=nvidia/nemotron-3.5-asr-streaming-multilingual-0.6b \
  -F response_format=json

Python (OpenAI SDK)

The official SDK's multipart upload works as is; just point base_url at deCloud.

from openai import OpenAI

client = OpenAI(base_url="https://macdecloud.com/v1", api_key="dcld-sk-...")
with open("meeting.mp3", "rb") as audio:
    resp = client.audio.transcriptions.create(model="nvidia/nemotron-3.5-asr-streaming-multilingual-0.6b", file=audio)
print(resp.text)