[ NVIDIA ]

Parakeet TDT 0.6B v3

Parakeet TDT 0.6B v3 from NVIDIA: a speech-to-text model that transcribes audio. Routed to the cheapest provider. At or below list. Priced in USD per minute of audio, paid in USDF, with no subscription and no minimum.

NVIDIAparakeet-tdt-0.6b-v3AvailabletranscriptionMax audio size: 25 MB

Input

$0.0015

per minute of audio

Max audio size

25

MB

Model ID
parakeet-tdt-0.6b-v3
Modality
transcription
Unit
USD per minute of audio
Endpoints
/v1/audio/transcriptions
Saving vs list
4.76%

Data policy

Zero retentionNo training

Make your first request

Responses include a receipt with the exact cost. No key yet? Create one.

No account: send the same request to /x402/v1/audio/transcriptions without credentials and the gateway answers 402 with the quote. Pay per request.

curl https://api.usdf.fi/v1/audio/transcriptions \
  -H "Authorization: Bearer $USDF_API_KEY" \
  -F model="parakeet-tdt-0.6b-v3" \
  -F file=@audio.mp3