Azure Speech 07 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 14, 2026Azure Speech 07 2026 is Microsoft's proprietary speech-to-text service that turns audio into written words across 25 languages. It performs better than most models on real-world audio like podcasts, meetings and accented speech, though its overall accuracy sits in the middle of the field.
Pick this for podcasts, video or meeting audio where it beats most alternatives, or for accented English. Use it for 25-language coverage, though non-English accuracy is unverified. Skip it if you need transparent pricing, fast turnaround, or top-tier overall accuracy — no speed or cost data is disclosed.
The case for it
- Better than most models on podcasts and video, meetings, and accented speech — the audio types people actually use.
- Very solid on clean read-aloud audio at 1.2% error, well under the field middle of 1.5%.
- 25 languages supported, broader than many transcription services.
The case against it
- Overall accuracy is middle-of-the-pack at 3.8% — roughly one word in 26 wrong, while the best models manage one in 28.
- No pricing, speed or release date disclosed; proprietary weights with zero tracked offers.
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 · 2nd of 76
- transcribing recordings of meetings in a roomRecorded meetings · 8th of 92
- transcribing speakers with a range of accentsAccented speech · 4th of 76
- transcribing podcasts and video audioPodcasts and video · 15th of 92
TranscriptionTurning speech into text4.5 of 5Open ASR WER · 2nd of 76
96.2%
Misses roughly one word in 26, 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 07 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 07 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-07-2026