Parakeet TDT 0.6b v2 (fast Gpu Asr)
NVIDIA
Speech to textTranscribes a recording into words
- Type
- Closed
- Input
- None held
- Output
- None held
- Cached
- None held
We don't hold a list price for this model yet · hosted only — we have no record of published weights
Our take
Written Sep 29, 2026Parakeet TDT 0.6b v2 is a speech-to-text model with a measured speed advantage: on the leaderboard's own hardware it transcribes an hour of audio in under a second. It is accurate on clearly recorded English, but we list no download and no host for it, so there is no route here to run it.
Reach for it when you are working through a long backlog of English recordings and speed matters more than the last fraction of a percent of accuracy, or when the audio is clearly recorded read-aloud speech, podcasts or video, where it sits better than most models on the condition. Skip it if you need a route to actually run it, or if you need transcription in a language other than English.
The case for it
- 14,199 times real time on the leaderboard's own hardware, so an hour of audio takes under a second there — a long backlog becomes practical to work through.
- 1.3% of words wrong on clean read-aloud recordings, better than most models on this condition, and 8.2% on podcast and video, also better than most.
- 6.8% of words wrong on accented speech and 9% on meeting recordings, both better than most models on those conditions.
The case against it
- We list no download for it and no host for it, so there is nothing here to run yourself or reach through an API.
- Every accuracy figure we hold is English; accuracy in any other language is unverified in our data.
- 4.7% of words wrong averaged over nine English test sets, against a field best of 3.6% and a middle of 5.2%.
How good is it?
TranscriptionTurning speech into text4 of 5Open ASR WER · 23rd of 76
95.3%
Misses roughly one word in 21, averaged over nine English test sets.
14,199×3rd of 74
an hour of audio in under a second, on the board's own hardware. Your machine will differ.
Percentage of words wrong on each set, lower better. Bars are scaled to this model's own worst case; the placing beneath each rate is against every model measured on that set.
The figures above come from the Open ASR Leaderboard, an independent public test that runs every model on the same recordings. It is the only measurement of transcription quality we know of, so there are no other scores to show.
Each of these is the same transcription job on a different kind of recording, so together they say where it holds up and where it slips — not how closely it follows an instruction.
Every published score for this model9 scoresEvery figure we hold, from 9 boards, with who ran it and a link to the source — including the boards no rating above is built on.
Where to get it
We hold no priced listing for Parakeet TDT 0.6b v2 (fast Gpu Asr).
There is no copy to download and no host in our price data, so NVIDIA is where to look. We watch OpenRouter, the provider APIs we track and the LiteLLM price set; this version appears in none of them, which is a gap in what we collect rather than a statement about what NVIDIA sells.
Models people weigh against Parakeet TDT 0.6b v2 (fast Gpu Asr)
When we formed this view
Recent changes
What moved
first indexed by our pipelineEach date is the day we first saw the change, or the day the maker announced it.
What we do not know about this model yet
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- We don't hold a list price for this model yet — the gap is ours, not the lab's.
Licence and identifiers
What the licence allowsWe hold no licence record for this model. Inside are the identifiers you need to pull it — its Hugging Face repo where we have one, our slug and a machine-readable card.
Licence
We hold no licence record for this model, and no record of published weights either — so we can neither summarise its terms nor point you at the weights.
Identifiers
- Takes in, gives back
- Audio in, text out
- Catalogue slug
- nvidia-parakeet-tdt-0-6b-v2-fast-gpu-asr