Scribe v3
Notable release: A meaningful new model: a new size or version, a strong open model, or a new image, video or audio model from a known lab.
ElevenLabs made Scribe v3, a tool that turns recorded speech into written text more accurately than its predecessor.
trckr spotted this 5 h 47 min before the official announcement (first seen via ElevenLabs blog).
Key facts
- Released
- Nov 10, 2026
- What it does
- Makes sound: Creates speech, music or other audio.
Can I use it?
Not yet
In an app
No app mentioned so far.
Not yet
For developers
No developer access mentioned so far.
No
Download
Not downloadable: it runs on the maker's own servers.
Compare Scribe v3 with
It came out 525 days after Eleven v3, the lab's previous model.
The details
ElevenLabs released Scribe v3, a Speech-to-text: Turns spoken audio into written text. Also called transcription or ASR. model for recorded audio, with 27% fewer word errors than Scribe v2.
Timeline
/ElevenLabs blogOfficialFirst signal
Introducing Scribe v3 and v3 Live, our most accurate speech to text models
Get alerts like this the moment they happen.
From ElevenLabs and every other major lab.
Free, no account needed. Push, Telegram, Discord, email or RSS.