Models / ElevenLabs/ Scribe v2

Scribe v2

ElevenLabs

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

Scribe v2 is ElevenLabs' proprietary speech-to-text model that turns audio into written words across 90 languages. It excels on clean, prepared English audio with near-perfect accuracy, but degrades sharply in meetings and with accented speech where no pricing or hosted access is currently available.

Who should pick it

Pick this for high-stakes transcription of clean, prepared English speech, or financial calls with controlled audio. Consider it for multilingual projects needing 90-language support, though accuracy is unverified beyond English. Skip it if you are transcribing meetings, podcasts, or accented speech, where error rates rise sevenfold to eightfold, or if you need a hosted option today.

The case for it

  • Near-perfect on clean, read-aloud English: about one word in a hundred wrong, and only slightly more on European-accented read speech.
  • Handles controlled difficult audio better than chaotic real-world audio: harder read speech at roughly a third the error rate of podcasts, video, or meetings.
  • Broad language support with 90 languages listed, though accuracy is measured only in English.

The case against it

  • Dramatically worse in uncontrolled real-world settings: meetings and accented speech see error rates roughly seven to eight times higher than clean read speech.
  • Accented speech is the worst-performing condition tested, with the highest error rate of any scenario.
  • No available pricing or hosted access in our data, and no release date or parameter count disclosed.
00

How good is it?

TranscriptionTurning speech into text4.5 of 5Open ASR WER · 7th of 74

Words it gets right

95.4%

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

Languages

90

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

Where it struggles
Read aloudaudiobooks, clean recording1.1%
Podcasts and videoeveryday internet audio7.6%
Accented speechspeakers from many countries8.9%
Meetingsa room, several people, far microphone8.2%

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 1st of 74Clean read speech 9th of 74Harder read speech 12th of 74Accented speech 13th of 74Recorded meetings 16th of 74Podcasts and video 18th of 74Financial calls 52nd 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.
4.6independentsource ↗
8.9independentsource ↗
3independentsource ↗
8.2independentsource ↗
7.6independentsource ↗
1.1independentsource ↗
2.3independentsource ↗
01

Where to get it

We hold no priced listing for Scribe v2.

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

02

When we formed this view

Dates behind this page

Aug 2, 2026BenchmarkScored 8.9 on Accented speechleaderboard
Aug 2, 2026BenchmarkScored 3 on Financial callsleaderboard
Aug 2, 2026BenchmarkScored 8.2 on Recorded meetingsleaderboard
Aug 2, 2026BenchmarkScored 1.4 on European-accented speechleaderboard
Aug 2, 2026BenchmarkScored 7.6 on Podcasts and videoleaderboard
Aug 2, 2026BenchmarkScored 1.1 on Clean read speechleaderboard
Aug 2, 2026BenchmarkScored 2.3 on Harder read speechleaderboard
Aug 1, 2026ListedListed on LLMapfirst indexed by our pipeline
Aug 1, 2026BenchmarkScored 4.6 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
elevenlabs-scribe-v2

Machine-readable model card (omc.json) →

Something wrong on this page? Tell us