Skip to content
English

Switch theme

// AI news · 2026-11-10 · ElevenLabs Blog

ElevenLabs launches Scribe v3 and v3 Live

ElevenLabs launches Scribe v3 and Scribe v3 Live, speech-to-text models with 27% fewer word errors than Scribe v2 across 102 languages.

Published 2026-11-10 20:00 (Beijing time)Source ElevenLabs BlogAuto-summarised, fact-checked against source

01Summary

Scribe v3 improves speaker diarization in multi-speaker meetings by 17%, while Scribe v3 Live introduces real-time diarization and context-aware turn detection. Both support multilingual switching, custom formatting, and keyword prompting with up to 1,000 terms or large-scale libraries. Performance is validated on FLEURS and custom meeting datasets across 16 languages.

Summarised from the original article by an open-source model, then checked automatically: every number and English name must appear in the source. The original article is authoritative.

02Key points

03Source

Introducing Scribe v3 and v3 Live, our most accurate speech to text models

ElevenLabs Blog · published 2026-11-10 20:00 Beijing time

Also reported by 2 other outlets

05Related news

From AIMap AI news: collected from 1,100+ official and media sources. Summaries only restate the original article; follow the link for the full story. All stories of 2026-11-10 · Archive by date · All AI news · Today

Data updated: AI news(UTC+8)