Scribe v2
ElevenLabs
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, 2026Scribe v2 is ElevenLabs' proprietary speech-to-text service that handles 90 languages and charges per minute of audio. It is a strong value pick for high-volume transcription, with better-than-most accuracy on several English audio conditions.
Pick this for high-volume transcription where per-minute cost matters, or for multilingual pipelines needing broad language coverage. Use it for clean read-aloud or European-accented English audio, podcasts, video, and meeting-room audio, where it outperforms most models on each condition. Skip it if you need open weights, alternative hosts for price competition, or verified accuracy outside English.
The case for it
- Among the lowest per-minute rates we hold for proprietary speech-to-text.
- Better than most models on read-aloud audio, with a word error rate below the median across 85 models.
- Better than most on European-accented parliamentary speech, podcasts, video, and real meetings.
- Better than most on accented earnings-call audio, well under the median across 69 models.
The case against it
- Never 'among the best' on any condition we measure — always 'better than most' with a gap to the top.
- Only one tracked offer, from ElevenLabs, so no alternative hosts or price competition.
- All accuracy figures are English; the 90-language claim is unverified in our data.
How good is it?
A speech-to-text model for turning recordings of meetings, podcasts and accented speakers into written text.
- turning spoken English into written textOpen ASR WER · 4th of 76
- transcribing recordings of meetings in a roomRecorded meetings · 22nd of 92
- transcribing speakers with a range of accentsAccented speech · 3rd of 76
- transcribing podcasts and video audioPodcasts and video · 21st of 92
- transcribing clear recordings of people reading aloudClean read speech · 12th of 92
TranscriptionTurning speech into text4.5 of 5Open ASR WER · 4th of 76
96%
Misses roughly one word in 25, averaged over nine English test sets.
90
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 rent it
Prices checked 2 hours ago
- per minute of audio
- $0.004
- Context served
- —
- Throughput
- Not measured
| Provider | Price per minute of audio | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| ElevenLabsDirect | $0.004checked 2 hours ago | not reported | not measured | Unknown | Unknown | Unknown |
Across the 1 listings we hold: 0 say they do not train on prompts, 0 say they do and 1 does not say. 0 appear in the zero-retention registry we check; the rest are unknown to us.
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
- 1 of 1 listings publishes no parameter list, so what its API accepts is unknown to us.
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 1 of 1 listings does not say whether it trains on prompts.
- We don't hold a list price for this model yet — the gap is ours, not the lab's.
- We hold no cached-input rate for any of its listings.
- We hold no batch or off-peak rate for any of its listings.
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
- elevenlabs-scribe-v2