# ElevenLabs releases Eleven Realtime speech-to-speech models

The models support over 90 languages and 17,000 voices via an OpenAI-compatible WebSocket API or ElevenAgents.

- Eleven Realtime v1 Max responds in 0.57 seconds, scoring 98.8% on Big Bench Audio reasoning and 87.1% on tool use.
- Eleven Realtime v1 Mini responds in 0.62 seconds, scoring 75.9% on reasoning and 95.8% on Full-Duplex-Bench for conversational dynamics.
- Deployments run through ElevenAgents across phone lines, websites, WhatsApp, and contact center platforms.

## Why it matters

Voice agent developers can replace multi-component audio pipelines with speech-to-speech models using existing OpenAI Realtime API integrations.

## Sources

- [ElevenLabs: ElevenLabs releases Eleven Realtime speech-to-speech models](https://x.com/ElevenLabs/status/2112550782063247521)

---

Summarized by dstilled on 2026-10-20. https://dstilled.ai/story/b6435048-b072-4c80-a7cc-1ef621459989