AINewsnow

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

This story is from 2026-11-12. It is preserved in the archive; the latest stories are on the live feed.

ElevenLabs released Scribe v3 for recorded audio and Scribe v3 Live for realtime transcription on November 10, designed to transcribe accurately through background noise and crosstalk, with Live using conversational context to avoid cutting off callers.

Read the full story at The Decoder ↗

Timeline · 2 reports

  1. 2026-11-12 18:00 · DEV Community — Machine Learning
    ElevenLabs launches Scribe v3 and Scribe v3 Live, its most accurate speech-to-text models yet
  2. 2026-11-12 13:48 · The Decoder
    ElevenLabs Scribe v3 Live uses conversational context to stop voice agents from cutting off callers mid-sentence

More stories

  1. ElevenLabs launches ElevenAI meeting notetaker and dictation app for teams — TechCrunch AI
  2. Optimizing ElevenLabs API Calls for Better Performance — DEV Community — AI
  3. ElevenLabs vs Google Cloud TTS: Developer Comparison — DEV Community — AI
  4. Create an AI Podcast Generator with ElevenLabs — DEV Community — AI
  5. An AI training crawler was 58% of my site's traffic. I charged it $0.001 a page and it left. — DEV Community — AI
  6. ElevenLabs + React: Building a Voice-Enabled UI — DEV Community — AI
  7. No ElevenLabs Coupon Code? I Sized My Plan With 40 Lines of Python Instead — DEV Community — AI
  8. How Content Creators Use ElevenLabs to Scale Video Production — DEV Community — AI

Get the daily brief of stories like this at 6:30 every morning →