Models / Microsoft/ Azure Speech 06 2026

Azure Speech 06 2026

Microsoft

Speech to textTranscribes a recording into words

Input: audio. Output: text.InputOutput
Type
Proprietary
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 Aug 2, 2026

Azure Speech is Microsoft's hosted-only transcription service that turns audio into text across 25 languages. It excels on clean, studio-quality narration with very low error rates, but degrades sharply on podcasts, meetings and accented speech where roughly one word in thirteen is wrong.

Who should pick it

Pick this for controlled-audio narration or audiobook work where the recording quality is high, or for multilingual deployments needing broad language coverage — though accuracy beyond English is unverified in our data. Skip it if you are transcribing natural conversation, accented speakers, or uncontrolled audio like podcasts and video, where error rates climb more than sixfold.

The case for it

  • Excellent on clean read-aloud audio, with a word error rate roughly a quarter of its own benchmark average.
  • 25 languages supported, broader coverage than most transcription services.

The case against it

  • Degrades sharply in natural, uncontrolled audio: podcasts and video run roughly six times the clean-speech error rate.
  • Accented speech is the worst condition measured, at over six times the clean-read rate.
  • No pricing or availability data: zero offers in our catalogue and no release date disclosed.
00

How good is it?

TranscriptionTurning speech into text5 of 5Open ASR WER · 3rd of 74

Words it gets right

95.5%

Misses roughly one word in 22, averaged over nine English test sets.

Languages

25

Stated by the leaderboard; we do not hold the list itself.

Where it struggles
Read aloudaudiobooks, clean recording1.2%
Podcasts and videoeveryday internet audio7.3%
Accented speechspeakers from many countries7.5%
Meetingsa room, several people, far microphone7%

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.

Also scored, on boards we give no mark for
Accented speech 1st of 74Recorded meetings 3rd of 74Podcasts and video 8th of 74Harder read speech 15th of 74Clean read speech 20th of 74Financial calls 26th of 74European-accented speech 41st of 74

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 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.
4.5independentsource ↗
7.5independentsource ↗
2.3independentsource ↗
7independentsource ↗
7.3independentsource ↗
1.2independentsource ↗
2.5independentsource ↗
01

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.

02

When we formed this view

Dates behind this page

Aug 2, 2026BenchmarkScored 7.5 on Accented speechleaderboard
Aug 2, 2026BenchmarkScored 2.3 on Financial callsleaderboard
Aug 2, 2026BenchmarkScored 7 on Recorded meetingsleaderboard
Aug 2, 2026BenchmarkScored 3.9 on European-accented speechleaderboard
Aug 2, 2026BenchmarkScored 7.3 on Podcasts and videoleaderboard
Aug 2, 2026BenchmarkScored 1.2 on Clean read speechleaderboard
Aug 2, 2026BenchmarkScored 2.5 on Harder read speechleaderboard
Aug 1, 2026ListedListed on LLMapfirst indexed by our pipeline
Aug 1, 2026BenchmarkScored 4.5 on Open ASR WERleaderboard

Prices last checked 6h ago

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.
03

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

Commercial API terms. We hold no licence record for this model, so there is nothing to summarise here.

Identifiers

Modality record
audio->text
Catalogue slug
microsoft-azure-speech-06-2026

Machine-readable model card (omc.json) →

Something wrong on this page? Tell us