Introducing Eleven Realtime, a new class of Speech to Speech models. Voice agents usually make you choose between quick replies or precise answers. Eleven Realtime gives you both. It starts talking in half a second and gets spoken reasoning questions right.
130
186
102
2,464
213,030
The future of voice AI is one system optimized end-to-end for more natural interactions at lower latency. Eleven Realtime v1 Max scores 98.8% on Big Bench Audio and starts speaking in 0.57s. No model on the Artificial Analysis leaderboard is both faster and more accurate.

Oct 20, 2026 · 2:25 PM UTC

4
2
5
69
10,637
RelevantRecentLikes
Eleven Realtime v1 mini is optimized for natural conversations at low cost. It handles the things that make a voice agent feel human, like knowing when you’ve finished speaking, recovering when you interrupt, and not stopping when you say “mm-hmm.” This model is great for AI assistants, educational tutors, and interactive characters.
3
1
36
5,311
Eleven Realtime v1 max is optimized for handling more complex tasks like customer support and lead qualification. It reasons through multi-step requests and calls tools to look things up and take action.
2
25
4,144
Both models are available in ElevenAgents today. Select Eleven Realtime as the model, and deploy production-ready agents anywhere your customers are: phone lines, your website, WhatsApp, or your contact center platform. Plus, you get the full platform features like knowledge bases, guardrails, testing, and monitoring.
1
30
3,778
Eleven Realtime is also available via the Realtime API. It’s OpenAI-compatible, so all you need to do is swap the endpoint and model name.
2
1
18
5,158
Try both models today: elevenlabs.io/realtime

Eleven Realtime | Speech to Speech Voice Agents | ElevenLabs

ElevenLabs Realtime: Instant conversation and Speech-to-Speech V1 Mini and V1 Max Models for Voice Agents

elevenlabs.io
1
1
26
4,827
finally voice ai without the awkward pause
72
Top accuracy at that speed is serious stuff for realtime narration
65