Scribe v2, Explained Simply
What Scribe v2 is, what it does well, and what it costs — released 2026-01-12 by ElevenLabs.
- ElevenLabs just released Scribe v2, their newest tool for turning spoken audio into text.
- It is designed to be their most advanced transcription model yet.
- It is mainly for developers, app makers, or anyone who needs highly accurate audio-to-text conversion.
Want a heads-up when ElevenLabs updates?
We email you the moment a new ElevenLabs version drops — plus plain-English release notes like these. No spam.
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
ElevenLabs is known for making realistic AI voices, but Scribe v2 is all about listening. It is a transcription model, which means it takes recorded speech and writes down exactly what was said. Anyone building apps that need to understand human speech—like video editors, podcasters, or companies recording customer service calls—would want to use this.
What it does well
- Turns spoken audio into written text.
- Represents the "state of the art," meaning it is designed to be a major step up in quality and accuracy compared to older tech.
Worth knowing
- The announcement is very brief, so specific details about supported languages, file sizes, or extra features are not included yet.
- You currently have to check out ElevenLabs' developer documentation to actually use it or figure out how to access it.
This is our plain-language summary. Read the complete, official notes on the ElevenLabs official changelog ↗.
Google Calendar