Models / NVIDIA/ Parakeet CTC 0.6b

Parakeet CTC 0.6b

NVIDIA · nvidia/parakeet-ctc-0.6b

Speech to textTranscribes a recording into words

Input: audio. Output: text.InputOutput
Type
Open weightsCreative Commons Attribution 4.0
Languages
1
Size
0.6B

Context measured in tokens

Our take

Written Aug 2, 2026

Parakeet CTC is a tiny downloadable speech-to-text model from NVIDIA that turns English audio into written text almost instantly. It excels on clean recordings but its accuracy drops sharply in meetings, podcasts or accented speech, and no hosts currently offer it as a paid service.

Who should pick it

Pick this for batch transcription of clean, read-aloud English audio where speed matters most — it processes an hour of audio in under a second on benchmark hardware. Use it for offline edge deployment where model size is critical, or for financial call transcription. Skip it if you need non-English languages, conversational or accented audio, or a hosted API.

The case for it

  • Extreme speed: 5,883.91 times real time on benchmark hardware.
  • Excellent on clean read-aloud audio, with about one word in sixty-four wrong.
  • Tiny at 0.6B parameters, enabling deployment on very small devices.
  • Permissive Creative Commons Attribution 4.0 licence allows commercial use with attribution.

The case against it

  • Accuracy collapses in recorded meetings and accented speech, with error rates more than eight times higher than on clean read-aloud audio.
  • English only — no accuracy data exists for any other language, and no hosted inference options are currently available.
00

How good is it?

TranscriptionTurning speech into text2 of 5Open ASR WER · 58th of 74

Words it gets right

93.3%

Misses roughly one word in 15, averaged over nine English test sets.

How fast it listens

5,884×4th of 62

an hour of audio in under a second, on the board's own hardware. Your machine will differ.

Languages

1

Listed on the model card. The accuracy above is English only.

Where it struggles
Read aloudaudiobooks, clean recording1.6%
Podcasts and videoeveryday internet audio8.9%
Accented speechspeakers from many countries13.5%
Meetingsa room, several people, far microphone13.1%

Percentage of words wrong on each set, lower better. Bars are scaled to this model's own worst case, not to the board.

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.

Also scored, on boards we give no mark for
European-accented speech 23rd of 74Harder read speech 39th of 74Clean read speech 46th of 74Recorded meetings 52nd of 74Podcasts and video 56th of 74Financial calls 58th of 74Accented speech 65th of 74

These tests check whether a model follows instructions — a precondition for all the work above, but not a measure of how well that work is done, which is why they get no rating.

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.
5883.9independentsource ↗
6.7independentsource ↗
13.5independentsource ↗
3.5independentsource ↗
13.1independentsource ↗
8.9independentsource ↗
1.6independentsource ↗
3.4independentsource ↗
01

Can you run it yourself?

Fits in memory
weights load entirely on the card
Spills to system RAM
some weights offload; much slower
Too large
will not load even with offload
est
size is calculated; the verdict could change by 10%

Comfortable fit

A card many people ownFits in memory

GeForce RTX 4090 · 24 GB

Weights at Q4_K_M0.4 / 24 GBest
Spare memory21.2 GB spare
Usable context262Kwhat the spare memory holds; no published limit on record
Decode speed2217 tok/sest

Room to spare. 21.2 GB spare means a 10% error in the size would not change the answer.

One step upFits in memory

Apple M1 Pro (16-core GPU) · 32 GB

Weights at Q4_K_M0.4 / 32 GBest
Spare memory22.4 GB spare
Usable context262Kwhat the spare memory holds; no published limit on record
Decode speed385 tok/sest

Room to spare. 22.4 GB spare means a 10% error in the size would not change the answer.

On a MacFits in memory

Apple M1 (8-core GPU, 8GB unified) · 8 GB

Weights at Q4_K_M0.4 / 8 GBest
Spare memory4.4 GB spare
Usable context262Kwhat the spare memory holds; no published limit on record
Decode speed131 tok/sest

Room to spare. 4.4 GB spare means a 10% error in the size would not change the answer.

Your hardware
Checking your profile…

Memory use by level

Against a 24 GB card.

Q4_K_M
recommended
0.4 GBest
Fits in memory
Q5_K_M
0.4 GBest
Fits in memory
Q8_0
0.7 GBest
Fits in memory

All 3 sizes here are calculated, not measured. We hold no measured file for this model, so each size comes from the parameter count and every verdict above inherits that uncertainty.

Check against your own machine → · All 71 devices, with every size →

02

Models people weigh against Parakeet CTC 0.6b

03

When we formed this view

Dates behind this page

Aug 2, 2026BenchmarkScored 13.5 on Accented speechleaderboard
Aug 2, 2026BenchmarkScored 3.5 on Financial callsleaderboard
Aug 2, 2026BenchmarkScored 13.1 on Recorded meetingsleaderboard
Aug 2, 2026BenchmarkScored 3.2 on European-accented speechleaderboard
Aug 2, 2026BenchmarkScored 8.9 on Podcasts and videoleaderboard
Aug 2, 2026BenchmarkScored 1.6 on Clean read speechleaderboard
Aug 2, 2026BenchmarkScored 3.4 on Harder read speechleaderboard
Aug 1, 2026ListedListed on LLMapfirst indexed by our pipeline
Aug 1, 2026BenchmarkScored 5883.9 on Open ASR RTFxleaderboard
Aug 1, 2026BenchmarkScored 6.7 on Open ASR WERleaderboard

Prices last checked 6h ago

What we do not know about this model yet

  • We hold no measured file for it, so all 3 sizes on this page are calculated from the parameter count.
  • Nothing we hold says whether an endpoint streams, so we do not show it either way.
04

Licence and identifiers

What the licence allowsCreative Commons Attribution 4.0, what it allows commercially, and the identifiers you need to pull this model — its Hugging Face repo, our slug and a machine-readable card.

Licence

Creative Commons Attribution 4.0

permissiveCommercial use allowed

Permissive content license: any use with attribution. Common for datasets and some model weights.

Identifiers

Modality record
audio->text
Catalogue slug
nvidia-parakeet-ctc-0-6b

Machine-readable model card (omc.json) →

Something wrong on this page? Tell us