AI brief
ElevenLabs released Eleven v4, a speech model that follows cues for laughter and whispering more accurately and maintains consistent voices across long productions such as audiobooks. A Turbo variant begins speaking in 150 milliseconds and is designed for real-time voice agents.
Why it matters: More expressive and consistent voices support long-form audio work, while the low-latency Turbo variant targets real-time voice agents.
Written by AI from The Decoder's published text.
Source
“Elevenlabs' new speech model, Eleven v4, follows cues for laughter and whispering more accurately and keeps voices consistent across long productions like audiobooks.”
Reporting from a publisher outside the organisation being covered.
Read original story ↗