Moonshine Streaming Tiny
Useful Sensors · released Jan 6, 2026 · usefulsensors/moonshine-streaming-tiny
Speech to textTranscribes a recording into words
- Type
- Open weightsMIT License
- Languages
- 1
- Size
- 0B
about 3K words of context
Our take
Written Sep 4, 2026Moonshine Streaming Tiny is a 30-million-parameter English speech-to-text model from Useful Sensors, released under a permissive MIT licence. It is built for raw speed on edge hardware, processing an hour of audio in under a second on the benchmark rig, though its accuracy trails most alternatives on every measured condition.
Choose this when transcription speed matters more than accuracy, or for offline edge deployment where a tiny model and permissive licence remove friction. It suits clean read-aloud audio best, where it gets about one word in twenty-five wrong. Skip it if you need hosted inference, multi-language support, or accuracy on meetings, podcasts or accented speech.
The case for it
- Extreme benchmark speed: 4,375 times real time on the leaderboard rig, or an hour of audio in under a second.
- MIT licence allows commercial use, modification and redistribution with minimal obligation.
- 30 million parameters fit easily into edge and mobile memory.
The case against it
- Worse than most models on every measured audio condition, from clean speech to meetings and accented audio.
- No hosted inference options listed; you must run it yourself.
- English only in our data; no measured accuracy for other languages.
How good is it?
An open speech-to-text model for turning recordings into text, though it trails most others on accuracy.
- turning spoken English into written textOpen ASR WER · 74th of 76
- transcribing recordings of meetings in a roomRecorded meetings · 83rd of 92
- transcribing speakers with a range of accentsAccented speech · 76th of 76
- transcribing podcasts and video audioPodcasts and video · 83rd of 92
- transcribing clear recordings of people reading aloudClean read speech · 87th of 92
TranscriptionTurning speech into text1 of 5Open ASR WER · 74th of 76
87.6%
Misses roughly one word in 8, averaged over nine English test sets.
4,445×16th 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 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?
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.
These cards answer whether Moonshine Streaming Tiny 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.
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 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-streaming-tiny
- Architecture
- Dense
- Takes in, gives back
- Audio in, text out
- Catalogue slug
- usefulsensors-moonshine-streaming-tiny