Elevenlabs Launches Eleven Realtime Speech-to-Speech Models for AI Conversations

Elevenlabs has announced the launch of its new Eleven Realtime speech-to-speech models, which are characterized by high speed and accuracy. The v1 Max model achieved a 98.8% accuracy rate on the Big Bench Audio benchmark, with a response time of 0.57 seconds. These models are superior to all others on the Artificial Analysis leaderboard, as no model is both faster and more accurate. This achievement reflects significant advancements in real-time speech-to-speech technology.