Speech-to-text (Scribe v2)
ElevenLabs Scribe v2 is a speech-to-text model: the Speech to Text API "turns spoken audio into text with state of the art accuracy", offering accurate transcription in 90+ languages, keyterm prompting, entity detection and audio tagging.
audio + video → text · made by ElevenLabs
$0.0037per minute
ElevenLabs
Sold by 1 way
| Seller | Lane | Rate |
|---|---|---|
| ElevenLabs api | batch | $0.0037per minuteelevenlabs.io · read 2026-08-24 |
Measured 1 standing
| Place | Board | Metric | Score |
|---|---|---|---|
| 1stof 65 | Open ASR Leaderboard · English short-form | avg (Average WER %) | 4.0614 |
About
Speech-to-text (Scribe v2) — a text model from ElevenLabs, placed 1st of 65 on Open ASR Leaderboard · English short-form.
It takes audio and video and returns text. The catalogue files it under transcribe. It stands 1st of 65 on Open ASR Leaderboard · English short-form.
Every current figure
- Maker
- ElevenLabs
- Register
- model
- Takes
- audio + video
- Returns
- text
- Licence
- not read
- Boards
- 1
- Best place
- 1st of 65 — Open ASR Leaderboard · English short-form
Known as 2 names
elevenlabs/scribe_v2scribe-v2