Parakeet TDT 1.1b
NVIDIA · released Jan 25, 2024 · nvidia/parakeet-tdt-1.1b
Speech to textTranscribes a recording into words
- Type
- Open weightsCreative Commons Attribution 4.0
- Languages
- 1
- Size
- 1.1B
Context measured in tokens
Our take
Written Sep 4, 2026Parakeet TDT is a tiny downloadable speech-to-text model from NVIDIA that turns audio into written words at extreme speed. It is built for bulk transcription of clean English audio where throughput matters more than perfection, with a permissive licence that only requires attribution.
Pick this for fast bulk transcription of clean read-aloud content or audiobooks, where it gets about one word in a hundred wrong. Use it for European-accented formal speech or podcast and video transcription at speed. Skip it if you need accented or meeting-room audio, more than one language, or any measured quality data for non-English speech.
The case for it
- Transcribes an hour of audio in under a second on the benchmark hardware we track.
- Excellent on clean read-aloud audio, at roughly a quarter of the typical model error rate for that condition.
- Better than most on podcasts and internet video, with an error rate well under half the worst in its class.
- Creative Commons Attribution licence allows commercial use with attribution.
The case against it
- Accented and meeting-room audio are weak spots, with error rates worse than most models and roughly double the best.
- Not among the best on any condition we measure — only 'better than most' on two.
- English only; no accuracy data for any other language.
How good is it?
An open transcription model for turning clear read-aloud recordings into written text.
- transcribing clear recordings of people reading aloudClean read speech · 11th of 92
TranscriptionTurning speech into text
4,529×14th of 74
an hour of audio in under a second, on the board's own hardware. Your machine will differ.
1
Listed on the model card. The accuracy above is English only.
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 model7 scoresEvery figure we hold, from 7 boards, with who ran it and a link to the source — including the boards no rating above is built on.
Can you run it yourself?
Comfortable fit
GeForce RTX 4090 · 24 GB
Room to spare. 20.9 GB spare means a 10% error in the size would not change the answer.
Apple M1 Pro (16-core GPU) · 32 GB
Room to spare. 22.1 GB spare means a 10% error in the size would not change the answer.
Apple M2 (8-core GPU, 8GB unified) · 8 GB
Room to spare. 4.1 GB spare means a 10% error in the size would not change the answer.
These cards answer whether Parakeet TDT 1.1b loads, not how fast it transcribes. Throughput figures for a transcription model come from its text decoder, so treat this as a fit answer rather than a speed one.
Memory use by level
Against a 24 GB card.
What is quantisation? →This model on every device we track71 devicesThe Q4 build most people download, on each device: what the weights come to, how much context the memory leaves, and whether it runs. Smallest device that runs it first. This is a fit answer: whether it loads, not how fast it transcribes.
Models people weigh against Parakeet TDT 1.1b
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
- 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.
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
Permissive content license: any use with attribution. Common for datasets and some model weights.
Identifiers
- Hugging Face
- nvidia/parakeet-tdt-1.1b
- Takes in, gives back
- Audio in, text out
- Catalogue slug
- nvidia-parakeet-tdt-1-1b