Skip to content

NVIDIA · Transcription

Parakeet TDT 0.6B v3

NVIDIA 🇺🇸TranscriptionOpen weights. The weights are publicly available in a Hugging Face repo.
From Venice's listing:
Parakeet TDT 0.6B v3 is NVIDIA's open-weight speech recognition model, with 600 million parameters and support for 25 European languages, which it detects on its own. It transcribes quickly, with punctuation and capitalization.
Market median price
$0.0015 /min
Max context
448
Listings
2
Providers
2

Evidence and sources

🤗 nvidia/parakeet-tdt-0.6b-v3Released 4 Aug 2025Maker HQ: US (source)
All rankings: #664 on OpenRouter today #696 on OpenRouter this week #758 on OpenRouter this monthSources: Together AI data, flex.ai API data, Venice.ai data, Hugging FacePrimary data from Together AI from flex.ai API: name, hugging face id from Venice.ai: primary mode, description from Hugging Face: release date

Advantages and trade-offs

Compared with 10 representative transcription models

Advantages

Open weights available

The weights are public. None of its peers say whether theirs are.

We only make a claim when there's enough data on models of the same type. Updated 22 Nov, 06:07 UTC.

Input & output

as stated by the model's providers
Audio
Text

Listings

 Together AInvidia/parakeet-tdt-0.6b-v3Sources: LiteLLM data, Together AI data448$0.0015
 Venicenvidia/parakeet-tdt-0.6b-v3Source: Venice.ai dataNot published by the provider$0.006

These providers advertise this model. Researchers have found some resellers serving a different, cheaper model, so see how to check whether a provider meets your needs.

Benchmarks

No benchmark scores yet.

Also known as: nvidia-parakeet-tdt-0-6b-v3, nvidia/parakeet-tdt-0.6b-v3, together_ai/nvidia/parakeet-tdt-0.6b-v3

Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works