Elevenlabs launches Eleven Realtime Mini and Max speech-to-speech models
Elevenlabs introduced two managed voice‑agent models, Mini and Max, under the Eleven Realtime brand on Tuesday. The Max variant achieved a 98.8% score on the Big Bench Audio benchmark with a 0.57‑second response time, claiming the best speed‑accuracy trade‑off on the Artificial Analysis leaderboard.
Why it matters: The models enable developers to build real‑time conversational AI with higher accuracy and lower latency.
Read the coverage
More in AI
AI10h ago4 sources
AI9h ago2 sources
