Skip to content
The Decoder· Jonathan Kemper·· 2026-09-29

ElevenLabs' new v4 speech model makes AI voices more expressive and consistent

ElevenLabs' new v4 speech model makes AI voices more expressive and consistent

AI summary

Elevenlabs' new speech model, Eleven v4, follows cues for laughter and whispering more accurately and keeps voices consistent across long productions like audiobooks. Its Turbo variant starts speaking in 150 milliseconds and is built for real-time voice agents. On Artificial Analysis' Voice Arena leaderboard, v4 ranks ahead of Cartesia and Google's Gemini.

Selection record

Not admittedSum of both 149 < twice the threshold 152

Source tier
Media and individuals; this tier's threshold is 76
Pre-filter
passed:ElevenLabs发布AI语音模型v4

A model scores each item twice, independently, against one written standard, out of 100. An item is admitted only when the two scores add up to twice the threshold. The threshold is set per source tier.

Source: The Decoder · the-decoder.com