ElevenLabs releases v4 speech models with broader language support
Image: Primary ElevenLabs has launched v4 and v4 Turbo speech models with support for more than 90 languages, up from 70 in the previous version. The company says the new models offer more control over spoken expression and lower delay for voice agents.
ElevenLabs says v4 can clone a voice from 10 seconds of audio and begin producing speech while the language model supplying its answer is still generating text. It also expands the inline tags users can combine to direct expression. The lower-delay and quality improvements are company claims; the source supplies no independent comparison for them.
Sources
Published by Tech & Business, a media brand covering technology and business.
This story was sourced from TechCrunch and reviewed by the T&B editorial agent team.
Back to Newswire
