AINewsnow

ElevenLabs ships Scribe v3 and Scribe v3 Live with lower transcription errors and 93 ms latency

ElevenLabs released Scribe v3 and realtime sibling Scribe v3 Live on 10 November 2026, cutting word errors by 27% for recordings and 43% for live audio across 102 languages, with diarization in streaming and 93 ms TTFS.

Read the full story at AlphaSignal ↗

Timeline · 3 reports

  1. 2026-11-11 14:23 · DEV Community — AI
    ElevenLabs Scribe v3 Live Lands at 93 ms TTFS — Dual-Track WASAPI Capture Still Sets the Overlay Floor
  2. 2026-11-11 07:19 · DEV Community — AI
    Claude Meetings Joins the Call — Your Overlay Still Lives on Dual-Track WASAPI Capture
  3. 2026-11-10 18:16 · AlphaSignal
    ElevenLabs' Scribe v3 Cuts Live Transcription Errors by 43% Across 102 Languages

More stories

  1. ElevenLabs launches Scribe v3 and v3 Live speech-to-text models with fewer errors — ElevenLabs Blog
  2. The phantom life of Alice Huang, alleged Chinese spy who had affair with Nvidia CEO — CSET Georgetown
  3. ElevenLabs launches Marketplace for enterprise AI applications — ElevenLabs Blog
  4. ElevenLabs unveils fine-tuning, Interaction Engine, Memory, Routines and ElevenAI at NYC Summit — ElevenLabs Blog
  5. ElevenLabs launches model customization, ElevenAI and partner program — Unite.AI
  6. ElevenLabs launches partner program with 550+ firms to speed enterprise AI agent adoption — ElevenLabs Blog
  7. McKinsey and ElevenLabs partner to scale enterprise conversational AI — ElevenLabs Blog
  8. ElevenLabs details enterprise voice AI deployments at Yahoo, Twilio and others — ElevenLabs Blog

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