Azure Speech 06 2026
Microsoft
Speech to textTranscribes a recording into words
- Type
- Closed
- Input
- None held
- Output
- None held
- Cached
- None held
We don't hold a list price for this model yet · hosted only — no weights published
Our take
Written Sep 17, 2026Microsoft's Azure Speech 06 2026 is a speech-to-text model with solid measured accuracy on English audio, better than most models on every recording condition we hold. The catch is that we list no download and no host for it, so there is no route here to actually run it.
Reach for it when you are transcribing clearly recorded English audio — read-aloud material, podcasts, video — or English meeting recordings, where its error rate is better than most models measured on those conditions. Skip it if you need a route to actually run it, since we list no download and no host, or if you need a language other than English, speaker labelling, timestamps or streaming.
The case for it
- On clean read-aloud recordings it gets 1.2% of words wrong, better than most models on that condition, so audiobooks and narrated material are where it looks strongest.
- Podcast and video audio comes out at 7.3% of words wrong, better than most of the field there, which makes everyday internet audio a reasonable fit.
- Meeting recordings land at 7% of words wrong, better than most models on that condition, though the whole field scores far worse on meetings than on clean speech.
The case against it
- We list no download and no host for it, so there is nothing here you can try — the accuracy figures describe a model you cannot currently reach through this page.
- Averaged over nine English test sets it sits at 4.3% of words wrong, above the middle of the field rather than at the top, where the best is 3.6%.
- Every accuracy figure is English only: the model lists 25 languages, but none of them are measured here, so accuracy elsewhere is unverified.
How good is it?
A speech-to-text model for turning recordings of meetings, podcasts and varied accents into written text.
- turning spoken English into written textOpen ASR WER · 8th of 76
- transcribing recordings of meetings in a roomRecorded meetings · 5th of 92
- transcribing speakers with a range of accentsAccented speech · 7th of 76
- transcribing podcasts and video audioPodcasts and video · 9th of 92
TranscriptionTurning speech into text4 of 5Open ASR WER · 8th of 76
95.7%
Misses roughly one word in 23, averaged over nine English test sets.
25
Stated by the leaderboard; we do not hold the list itself.
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 model8 scoresEvery figure we hold, from 8 boards, with who ran it and a link to the source — including the boards no rating above is built on.
Where to get it
We hold no priced listing for Azure Speech 06 2026.
There is no copy to download and no host in our price data, so Microsoft is where to look. We watch OpenRouter, the provider APIs we track and the LiteLLM price set; this version appears in none of them, which is a gap in what we collect rather than a statement about what Microsoft sells.
Models people weigh against Azure Speech 06 2026
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
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- We don't hold a list price for this model yet — the gap is ours, not the lab's.
Licence and identifiers
What the licence allowsWe hold no licence record for this model. Inside are the identifiers you need to pull it — its Hugging Face repo where we have one, our slug and a machine-readable card.
Licence
We hold no licence row of this model's own. A source states its weights are not published, so the determination that governs it is the one for closed weights, API access only.
Identifiers
- Takes in, gives back
- Audio in, text out
- Catalogue slug
- microsoft-azure-speech-06-2026