Moonshine Tiny
Useful Sensors · usefulsensors/moonshine-tiny
Speech to textTranscribes a recording into words
- Type
- Open weightsMIT License
- Languages
- 1
- Size
- 30M
Context measured in tokens
Our take
Written Aug 2, 2026Moonshine Tiny is a 30-million-parameter speech-to-text model that turns audio into written words under a permissive MIT licence. It is built for speed, processing an hour of audio in under a second on benchmark hardware, though its accuracy varies sharply with audio quality.
Pick this for local or embedded transcription where speed trumps perfection, or for batch-processing large audio archives on modest hardware. Use it when the recording is clean read-aloud speech, where it gets about one word in twenty-five wrong. Skip it if you are transcribing meetings, accented speech, or podcasts, where roughly one in five to one in eight words may be incorrect, or if you need languages other than English.
The case for it
- Processes an hour of audio in under one second on benchmark hardware, at 3,733 times real time.
- Strong on clean read-aloud audio, with about a quarter of its overall error rate.
- MIT licence allows commercial use, modification and redistribution without restriction.
- 30 million parameters fits comfortably on edge devices and modest hardware.
The case against it
- Accuracy collapses on challenging audio: roughly one in five words wrong on accented speech and recorded meetings, nearly five times worse than on clean speech.
- Only English is covered; no measured accuracy for any other language.
- No commercial hosting available in our catalogue, so you must self-host.
How good is it?
TranscriptionTurning speech into text1 of 5Open ASR WER · 71st of 74
88.6%
Misses roughly one word in 9, averaged over nine English test sets.
3,733×12th of 62
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, 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.
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.
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
GeForce RTX 4090 · 24 GB
Room to spare. 21.6 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. 22.8 GB spare means a 10% error in the size would not change the answer.
Apple M1 (8-core GPU, 8GB unified) · 8 GB
Room to spare. 4.8 GB spare means a 10% error in the size would not change the answer.
Memory use by level
Against a 24 GB card.
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 →
When we formed this view
Dates behind this page
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.
Licence and identifiers
What the licence allowsMIT License, 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
MIT License
Fully permissive: do anything with attribution. No patent grant, unlike Apache-2.0.
Identifiers
- Hugging Face
- usefulsensors/moonshine-tiny
- Modality record
- audio->text
- Catalogue slug
- usefulsensors-moonshine-tiny