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
Threshold 76Media and individualsFirst 78Second 71
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