ElevenLabs Launches Realtime Speech-to-Speech Models for Low-Latency AI Conversations

1 reports archived1 independent sourcesupdated 10/21/2026, 03:03:15

Synthesis & Latest Updates

1 Sources Cross-Validated

ElevenLabs released two new speech-to-speech models, Eleven Realtime v1 Max and Mini, designed to optimize response speed and accuracy in AI conversations. The Max variant achieves a 98.8% score on the Big Bench Audio benchmark with a 0.57-second latency, while the Mini focuses on cost-effective natural interactions and turn-taking detection. Both are accessible via the ElevenAgents platform and an OpenAI-compatible Realtime API.

LATEST/ElevenLabs released two new speech-to-speech models, Eleven Realtime v1 Max and Mini, designed to optimize response speed and accuracy in AI conversations. The Max variant achieves a 98.8% score on the Big Bench Audio benchmark with a 0.57-second latency, while the Mini focuses on cost-effective natural interactions and turn-taking detection. Both are accessible via the ElevenAgents platform and an OpenAI-compatible Realtime API.

HEAT TRENDHourly heat curve

2 fully observed hours

Fewer than 3 fully observed hours; trend not plotted yet.

TIMELINECoverage timeline

Total 1 reports · Latest first

The DecoderT2·Oct 21, 03:0372 pts
ElevenLabs Launches Realtime Speech-to-Speech Models for Low-Latency AI Conversations
- Eleven Realtime v1 Max scores 98.8% on the Big Bench Audio benchmark with a low latency of 0.57 seconds.
- The v1 Mini model is optimized for cost-effective natural conversations, capable of detecting turn-taking cues like 'mm-hmm'.
- Both models are available through the ElevenAgents platform and an OpenAI-compatible Realtime API.
View Related Reports & Analysis Original Source