Cohere Transcribe 03 2026
Cohere Labs · released Mar 24, 2026 · CohereLabs/cohere-transcribe-03-2026
Speech to textTranscribes a recording into words
- Type
- Open weightsApache License 2.0
- Languages
- 14
- Size
- 2.1B
Context measured in tokens
Our take
Written Aug 3, 2026Cohere Transcribe 03 2026 is a 2.1-billion-parameter speech-to-text model with an Apache licence, built for speed and clean-read accuracy. It turns audio into text across 14 languages, though every accuracy figure we hold is for English only.
Pick this for high-throughput batch transcription where speed matters — it processes an hour of audio in about four seconds. Use it for clean read-aloud audio at under one per cent error, or for projects needing a permissive licence. Skip it if you are transcribing accented speech, podcasts or meetings, where error rates rise sharply, or if you need hosted inference.
The case for it
- Extremely fast: processes an hour of audio in roughly four seconds on benchmark hardware.
- Near-perfect on clean read-aloud audio, at roughly one word wrong per hundred.
- Apache 2.0 licence allows commercial use, fine-tuning and redistribution without restriction.
- 14 languages supported, including Arabic, German, Greek, English, Spanish, French, Italian and Japanese.
The case against it
- Accuracy collapses on accented speech — more than five times worse than on clean read audio.
- Struggles in conversational and multi-speaker settings, with error rates more than eight times higher.
- No hosted inference available; must self-host, and all accuracy figures are English only.
How good is it?
TranscriptionTurning speech into text4 of 5Open ASR WER · 22nd of 74
94.8%
Misses roughly one word in 19, averaged over nine English test sets.
916×24th of 62
an hour of audio in 4 seconds, on the board's own hardware. Your machine will differ.
14
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.
Which languages ↓ ↑
Arabic · German · Greek · English · Spanish · French · Italian · Japanese · Korean · Dutch · Polish · Portuguese · Vietnamese · Chinese
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. 20.2 GB spare means a 10% error in the size would not change the answer.
GeForce RTX 5090 · 32 GB
Room to spare. 28.2 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. 3.4 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
- CohereLabs/cohere-transcribe-03-2026
- Modality record
- audio->text
- Catalogue slug
- coherelabs-cohere-transcribe-03-2026