Skip to content
FluxCDNFluxCDN
esc

NVIDIA: Nemotron 3.5 Transcribe

Speech to text

Nemotron 3.5 Transcribe is an open-weight speech recognition model from NVIDIA, a 30B mixture-of-experts with about 4B active parameters.

Price
361 Toman a minute of audio
Endpoint
POST /v1/audio/transcriptions
Published
Oct 29, 2026
Offers
With segment and word times
Maker
NVIDIA

Free plan prices, in Toman at today's rate. Plans and prices

Price on each plan

Per millisecond of audio heard, shown a minute at a time, in Toman at today's rate; never below what the provider charges us plus your plan's margin.

PlanPrice
Free361 Toman a minute of audio
Pro346 Toman a minute of audio
Max331 Toman a minute of audio

Call it

curl https://ai.fluxcdn.cloud/api/v1/audio/transcriptions -H "Authorization: Bearer $FLUXCDN_API_KEY" \
  -F file=@voice.mp3 -F model=nvidia/nemotron-3.5-transcribe -F language=fa \
  -F response_format=srt