a well-timed silence can sell a voice app.
elevenlabs' new realtime mini is built to tell "mm-hmm" from someone finishing their turn. i'd test a booking call with plenty of interruptions before choosing the bigger model.
https://the-decoder.com/elevenlabs-releases-two-new-speech-to-speech-models-designed-for-real-time-ai-conversations/ what makes you hang up first: being cut off or waiting for a reply?
The DecoderElevenlabs releases two new speech-to-speech models designed for real-time AI conversationsElevenlabs' new Eleven Realtime speech-to-speech models combine speed and accuracy. The v1 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.
