Elevenlabs has unveiled two new speech-to-speech models, named Eleven Realtime, which are specifically designed for real-time AI conversations. The v1 Max variant of these models achieved a remarkable 98.8 percent score on the Big Bench Audio benchmark, coupled with a response time of just 0.57 seconds. This performance positions Elevenlabs’ models as the fastest and most accurate in the current Artificial Analysis leaderboard.
The introduction of these models marks a significant advancement in AI-driven communication technologies, enabling more seamless interactions in various applications, from customer service to personal assistants. Elevenlabs emphasizes that no other existing model combines such speed and accuracy, setting a new standard in the industry.
Compiled automatically by the Tech AI Newsdesk from public AI-news sources and summarised in our own words.
