# ElevenLabs launches Scribe v3 and Scribe v3 Live speech-to-text models

Canonical: https://theagenticweekly.com/news/elevenlabs-scribe-v3-speech-to-text · Evidence: Reported · First seen: 2026-11-10 18:07 UTC · Source published: 2026-11-10 12:00 UTC · Brief published: 2026-11-11 06:06 UTC · Updated: 2026-11-11 06:06 UTC · Author: Agentic Weekly

> ElevenLabs launched Scribe v3 and Scribe v3 Live on Nov 10, 2026, calling them "our most accurate speech to text models." The company says Scribe v3 makes 27% fewer word errors than Scribe v2 across 102 languages, and Scribe v3 Live 43% fewer errors than Scribe v2 Realtime.

Models in this brief: [Scribe v3](https://theagenticweekly.com/models/scribe-v3), [Scribe v3 Live](https://theagenticweekly.com/models/scribe-v3-live)

## What changed

- Scribe v3 is the new model for recorded audio. ElevenLabs says it makes 27% fewer word errors than Scribe v2 across 102 languages on an internal version of the FLEURS benchmark, improving in every language it tested.
- Scribe v3 Live is the low-latency realtime variant. The post says it cuts semantic word error rate by 43% and WER by 31% versus Scribe v2 Realtime, and adds speaker diarization to realtime transcription for the first time.
- Turn detection in Scribe v3 Live uses conversation context as well as audio, so a caller who pauses mid-number is not cut off. ElevenLabs says this is the turn detection ElevenAgents already used, now exposed in ElevenAPI.
- Keyterm prompting takes up to 1,000 terms, transcript edits apply formatting rules written in plain English, and numbers can return as digits or words. Scribe v3 Live adds a multilingual mode for mid-sentence language switching and a keyterm library for larger vocabularies.
- On diarization, the post reports 12% fewer errors than Scribe v2 overall and 17% fewer on recordings with three or more speakers; Scribe v3 Live scored a 3.1% diarization error rate on English real-world audio versus 5.9% to 7.3% for other realtime models tested.
- Both models are in ElevenAPI today and are the default in the ElevenLabs app; existing integrations switch by changing the model ID to scribe_v3 or scribe_v3_live. They run in the US by default, with isolated EU, India and Singapore environments for enterprise data residency.

## In the source's words

> "In languages easier to transcribe, German improved by 42%, Spanish by 35%, and English by 23%."
> (ElevenLabs blog, Introducing Scribe v3 and v3 Live, https://elevenlabs.io/blog/scribe-v3)

## What we have not verified

- We did not run Scribe v3 or Scribe v3 Live; every accuracy, WER and diarization figure is from ElevenLabs' own evaluations, including an internal version of FLEURS and an in-house dataset that is not yet public.
- The post does not state per-minute or per-hour pricing for either model.
- The customer result (40% more Dutch postcodes recognized on first try) is a vendor-reported pre-launch test that we could not check.
- ElevenLabs says it will open source its 16-language real-world dataset soon; no date or link was given.

## Timeline

- Source published: 2026-11-10 12:00 UTC
- First seen by our watcher: 2026-11-10 18:07 UTC (via ElevenLabs blog)
- Brief published: 2026-11-11 06:06 UTC

## Sources

- [ElevenLabs blog: Introducing Scribe v3 and v3 Live](https://elevenlabs.io/blog/scribe-v3) (primary source) (fetched 2026-11-11)

## Related

- [Scribe v3: specs, price and alternatives](https://theagenticweekly.com/models/scribe-v3)
- [Scribe v3 Live: specs, price and alternatives](https://theagenticweekly.com/models/scribe-v3-live)
- [ElevenLabs: verdict and setup guide](https://theagenticweekly.com/tools/elevenlabs)
- [All news briefs](https://theagenticweekly.com/news)
- [New AI models this week](https://theagenticweekly.com/models/this-week)
- [AI model releases by month](https://theagenticweekly.com/models/releases)
- [Best LLM for coding](https://theagenticweekly.com/best/llm-for-coding)

## How to cite

Agentic Weekly, "ElevenLabs launches Scribe v3 and Scribe v3 Live speech-to-text models", published 2026-11-11 06:06 UTC, https://theagenticweekly.com/news/elevenlabs-scribe-v3-speech-to-text