Models / Speechmatics/ Speechmatics Enhanced

Speechmatics Enhanced

Speechmatics

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

Speechmatics Enhanced is a hosted-only speech-to-text engine that turns audio into written words across 55 languages. It excels on clean, read-aloud English with a very low error rate, but accuracy drops sharply in meetings and on heavily accented speech. No pricing or hosted access is currently available in our data.

Who should pick it

Pick this for clean narration or audiobook transcription, or European-accented English where it outperforms its own accented-speech average. Consider it for multilingual deployments needing 55 languages where English accuracy matters most. Skip it if you need meeting transcription, heavily accented speech, or transparent pricing and immediate hosted access.

The case for it

  • Excellent on clean read-aloud English: roughly three times better than its own overall average.
  • Strong on European-accented English, with a marked gap over accented speech generally.
  • 55 languages supported, which few transcription engines match.

The case against it

  • Accuracy collapses in recorded meetings and on heavily accented speech, with the latter more than six times worse than its clean-speech performance.
  • Large performance gap across conditions makes it inconsistent in practice.
  • No pricing or hosted access currently available in our data.
00

How good is it?

TranscriptionTurning speech into text3 of 5Open ASR WER · 41st of 74

Words it gets right

94.1%

Misses roughly one word in 17, averaged over nine English test sets.

Languages

55

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

Where it struggles
Read aloudaudiobooks, clean recording1.7%
Podcasts and videoeveryday internet audio7.8%
Accented speechspeakers from many countries11.9%
Meetingsa room, several people, far microphone10%

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
European-accented speech 16th of 74Podcasts and video 22nd of 74Recorded meetings 34th of 74Accented speech 48th of 74Financial calls 49th of 74Clean read speech 55th of 74Harder read speech 55th 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.
5.9independentsource ↗
11.9independentsource ↗
2.8independentsource ↗
10independentsource ↗
7.8independentsource ↗
1.7independentsource ↗
4.3independentsource ↗
01

Where to get it

We hold no priced listing for Speechmatics Enhanced.

There is no copy to download and no host in our price data, so Speechmatics 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 Speechmatics sells.

02

When we formed this view

Dates behind this page

Aug 2, 2026BenchmarkScored 11.9 on Accented speechleaderboard
Aug 2, 2026BenchmarkScored 2.8 on Financial callsleaderboard
Aug 2, 2026BenchmarkScored 10 on Recorded meetingsleaderboard
Aug 2, 2026BenchmarkScored 2.8 on European-accented speechleaderboard
Aug 2, 2026BenchmarkScored 7.8 on Podcasts and videoleaderboard
Aug 2, 2026BenchmarkScored 1.7 on Clean read speechleaderboard
Aug 2, 2026BenchmarkScored 4.3 on Harder read speechleaderboard
Aug 1, 2026ListedListed on LLMapfirst indexed by our pipeline
Aug 1, 2026BenchmarkScored 5.9 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
speechmatics-enhanced

Machine-readable model card (omc.json) →

Something wrong on this page? Tell us