NVIDIA: Parakeet TDT 0.6B v3

Live

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

Start generating See pricing

FreeInd is an independent platform and is not affiliated with, endorsed by, or sponsored by NVIDIA or the creators or owners of NVIDIA: Parakeet TDT 0.6B v3. The NVIDIA name and mark appear solely to identify the integrations available on this platform.

Rate: 7 credits; per generation
Modality: Text; Text generation
Availability: Live; ready to generate on FreeInd
Provider routes: 1; single routing provider

Capabilities

The generation modes and formats NVIDIA: Parakeet TDT 0.6B v3 supports on this platform.

Audio to Text

More from NVIDIA

Other live NVIDIA models on the platform.

All NVIDIA models

NVIDIA: Nemotron 3.5 Content Safety7 credits NVIDIA: Nemotron 3 Nano 30B A3B7 credits NVIDIA: Nemotron 3.5 ASR Streaming Multilingual 0.6B7 credits NVIDIA: Nemotron 3.5 Lightning7 credits NVIDIA: Nemotron 3 Nano Omni7 credits NVIDIA: Nemotron 3 Ultra7 credits

Other makers

Continue browsing the catalog by original model maker.

OpenAI(108)Google(49)Meta(8)Black Forest Labs(8)xAI(14)ByteDance(13)Kling AI(3)MiniMax(13)