Skip to content
assaynotes
EN日本語中文

ElevenLabs releases two realtime speech-to-speech models

Developing1 reports1 sourcesupdated 5 h ago

What happened

AI digest

On 21 October 2026, The Decoder reported that ElevenLabs has released two realtime speech-to-speech models, Eleven Realtime. According to the report, v1 Max scores 98.8% on the Big Bench Audio benchmark with a response time of 0.57 seconds. The report discloses only the release information and benchmark figures above, with no further details on how the two models differ in name, their availability or a launch date.

Written by AI from the reports · updated 2 h ago

LatestOct 21 03:03
ElevenLabs releases two Eleven Realtime models, with v1 Max scoring 98.8% on the benchmark and responding in 0.57 seconds.

Timeline

Follow the reports to see the event from each side.

Oct 21
  1. The Decoder
    Elevenlabs releases two new speech-to-speech models designed for real-time AI conversations

    Elevenlabs' new Eleven Realtime speech-to-speech models combine speed and accuracy. The v1 Max variant scores 98.8 percent on the Big Bench Audio benchmark with a 0.57-second response time. Elevenlabs says no model on the Artificial Analysis leaderboard is both faster and more accurate.

Heat of this event

Not enough continuous observations yet to draw a trend.