ElevenLabs V4 Needs Just 10 Seconds to Clone a Voice

ElevenLabs V4 Needs Just 10 Seconds to Clone a Voice

ElevenLabs has released v4 and v4 Turbo, text-to-speech models — software that turns text into spoken audio — built on a new design for faster cloning. V4 copies a voice from 10 seconds of sample audio, easing setup demands for production work where long, clean recordings are scarce.

Published

Read at another depth