ElevenLabs launches Eleven Realtime v1 Mini and Max speech-to-speech models
ElevenLabs released Eleven Realtime, a speech-to-speech model line with v1 Mini for lower-cost natural conversation and v1 Max for customer support and multi-step tasks, on October 20, 2026. Both models are available through the ElevenAgents platform and an OpenAI-compatible Realtime API, priced per minute plus token costs, with Max costing more than Mini. According to Artificial Analysis independent testing reported by 智东西, Max scored 98.8% on Big Bench Audio with a 0.57-second average first-audio response, placing third behind StepAudio 3 Realtime at 99.7% and Qwen Audio 3.0 Realtime Plus at 99.2%, while Mini scored 75.9%; ElevenLabs separately claimed no model on the Artificial Analysis leaderboard is both faster and more accurate, and 智东西's hands-on test of the Architect setup assistant found voice editing convenient but noted a noticeable Chinese accent, long replies and latency.
ElevenLabs is pitching Realtime as a way to simplify voice-agent building by letting developers choose Mini or Max instead of selecting each underlying component, while independent testing places Max third on Big Bench Audio.
Elevenlabs releases two new speech-to-speech models designed for real-time AI conversations
Matthias Bastian View the LinkedIn Profile of Matthias Bastian
Oct 20, 2026
Elevenlabs released two new speech-to-speech models called Eleven Realtime. The 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 right now.
The smaller v1 Mini is built for natural conversations at lower cost and can tell when someone's done talking or just saying "mm-hmm." V1 Max targets more complex tasks like customer support.
#ElevenLabs#Eleven Realtime v1 Max#Eleven Realtime v1 Mini#Artificial Analysis#ElevenAgents#StepAudio 3 Realtime#Qwen Audio 3.0 Realtime Plus#OpenAI Realtime API#Architect