Skip to content
FluxCDNFluxCDN
esc

NVIDIA: Parakeet TDT 0.6B v3

Speech to text

Parakeet TDT 0.6B v3 is NVIDIA's 600M-parameter multilingual speech-to-text model built on the FastConformer-TDT architecture.

Price
361 Toman a minute of audio
Endpoint
POST /v1/audio/transcriptions
Published
May 27, 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/parakeet-tdt-0.6b-v3 -F language=fa \
  -F response_format=srt