Elevenlabs launches real-time speech-to-speech models

elevenlabs released two new speech-to-speech models, eleven realtime v1 max and v1 mini, designed for real-time ai conversations. v1 max scores 98.8% on big bench audio benchmark with 0.57-second response time, making it one of the most accurate and fastest models on artificial analysis leaderboard. v1 mini is built for natural conversations at lower cost, while v1 max targets complex tasks like customer support. both models are available through elevenagents platform and openai-compatible api, with pricing per minute plus token costs.