Model dossier

NVIDIA: Parakeet TDT 0.6B v3

Parakeet TDT 0.6B v3 is NVIDIA's 600M-parameter multilingual speech-to-text model built on the FastConformer-TDT architecture. Trained on the Granary dataset (670,000+ hours of audio), it supports automatic language detection across...

ProviderNVIDIA Start comparison

Context0

Max outputn/a

Pricing viewTVP price

Identity

NVIDIA: Parakeet TDT 0.6B v3

Model ID: nvidia/parakeet-tdt-0.6b-v3
Canonical slug: nvidia/parakeet-tdt-0.6b-v3
Knowledge cutoff: n/a
Created: 5/27/2026

Capabilities

audiotranscription

Modalities

audio->transcriptionaudiotranscription

Capacity

Context0

Max outputn/a

TokenizerOther