ModelsSep 28, 2026 · 22:051 source

ElevenLabs Eleven v4 Takes No. 1 Voice AI Rank With Pronunciation Record

From huggingnews.com

Image: huggingnews.com
AI;DR

ElevenLabs' Eleven v4 text-to-speech model reached the No. 1 spot on Artificial Analysis' provider voice Elo leaderboard with a score of 1,319, surpassing Cartesia's Sonic 3.6 and Google's Gemini 3.8 Flash TTS. The model also achieved a pronunciation robustness score of 91.7%, the highest ever recorded by the analysis firm, and expanded language support to more than 90 languages while increasing generation speed to 73.4 characters per second. Eleven v4 is ranked No. 2 in the controlled voice category behind Alibaba's Qwen-Audio-3.1-TTS-Plus.

Read the sourceSign in to suggest

Sources

#llmMarkdown
Content history (2)
  • 2026-10-04 · Summary · vi · Replaced stored text
    Eleven v4 đạt điểm Provider Voice Elo 1.319, vượt mặt Sonic 3.6 của Cartesia và Gemini 3.…
    Chỉ số Provider Voice Elo của Eleven v4 đạt 1.319, vượt qua Sonic 3.6 của Cartesia và Gem…
  • 2026-10-04 · Title · vi · Replaced stored text
    ElevenLabs Eleven v4 lên ngôi quán quân Voice AI với kỷ lục phát âm
    ElevenLabs Eleven v4 đạt vị trí số 1 về voice AI với kỷ lục phát âm

One ranked edition, every morning

The stories that matter today. Free, cancel anytime.

Telegram @aidr_today