MOSS Transcribe Preview 2B
OpenMOSS · released Jun 26, 2026 · OpenMOSS-Team/MOSS-Transcribe-preview-2B
Speech to textTranscribes a recording into words
- Type
- Open weightsApache License 2.0
- Languages
- 1
- Size
- 2.4B
Context measured in tokens
Our take
Written Aug 2, 2026MOSS Transcribe Preview is a downloadable speech-to-text model from OpenMOSS that turns audio into written words. It is extremely fast and accurate on clean recordings, but its error rate rises sharply on difficult audio and it is only available in English.
Pick this for fast batch transcription of clean, scripted audio where a little over one word in a hundred may be wrong. Use it for financial call transcription or any self-hosted deployment that needs a permissive Apache licence. Skip it if you are transcribing meetings, accented speech, or any language other than English.
The case for it
- Extremely fast: one hour of audio in approximately 24 seconds on the benchmark hardware.
- Strong on clean read-aloud speech, with a word error rate roughly a quarter of its own overall average.
- Permissive Apache 2.0 licence allows commercial use, modification and redistribution.
- Handles financial calls well relative to other conditions, at 1.61% word error rate.
The case against it
- Accuracy collapses on challenging real-world audio: word error rate on accented speech is nearly seven times worse than on clean read speech.
- No hosted offers available; you must self-host.
- Only one language is covered, and every accuracy figure is English-only with no measurement of other languages.
How good is it?
TranscriptionTurning speech into text4.5 of 5Open ASR WER · 10th of 74
95.3%
Misses roughly one word in 21, averaged over nine English test sets.
149×52nd of 62
an hour of audio in 24 seconds, 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. 19.1 GB spare means a 10% error in the size would not change the answer.
GeForce RTX 5090 · 32 GB
Room to spare. 27.1 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. 2.3 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 allowsApache License 2.0, 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
Apache License 2.0
Fully permissive: commercial use, redistribution, and derivatives allowed. Requires attribution and a copy of the license. Includes an express patent grant.
Identifiers
- Hugging Face
- OpenMOSS-Team/MOSS-Transcribe-preview-2B
- Architecture
- Dense
- Modality record
- audio->text
- Catalogue slug
- openmoss-team-moss-transcribe-preview-2b