# Eleven v4 leads Artificial Analysis Provider Voice and pronunciation tests

Artificial Analysis says ElevenLabs’ Eleven v4 text-to-speech model, with support for more than 90 languages, ranks first on its Provider Voice arena and Pronunciation Robustness benchmark, and second on Controlled Voice.

Language: en
Time zone: America/Los_Angeles
Current time (UTC, cached as of): 2026-11-17T15:11:00.000Z
Query date (America/Los_Angeles): 2026-11-17

HTML: https://didcodexreset.com/news/64d4faee4c644fc28ad354c2.html

Content language: en
Localization state: sameLanguage

Source: Artificial Analysis · Published 9/28/2026, 07:39:29

Artificial Analysis ranks ElevenLabs’ Eleven v4 first on the Provider Voice TTS Arena with an Elo of 1,319 (+19/-19) across 1,674 appearances, ahead of Cartesia’s Sonic 3.6 at 1,276 and Google’s Gemini 3.8 Flash TTS at 1,267. It also ranks first in all four categories: Customer Service, Assistants, Knowledge Sharing, and Entertainment.

On Controlled Voice, where every model uses the same custom voice, Eleven v4 is second with an Elo of 1,157 (+16/-16) across 1,483 appearances, behind Alibaba’s Qwen-Audio-3.1-TTS-Plus at 1,178 and ahead of Eleven v3 at 1,073.

On Pronunciation Robustness, Artificial Analysis measures Eleven v4 at 91.7%, which it calls the highest score it has recorded, ahead of Gemini 3.8 Flash TTS at 89.5% and Gemini 3.1 Flash TTS at 88.2%, and up from Eleven v3 at 85.6%. Eleven v4 supports more than 90 languages, up from more than 70 for Eleven v3. Artificial Analysis lists its price at $80 per million characters, compared with $49 for Sonic 3.6 and $16.49 for Gemini 3.8 Flash TTS, and a generation speed of 73.4 characters per second, compared with 42.5 for Eleven v3.

Tags: ElevenLabs, Eleven v4, Text-to-speech, Artificial Analysis, Benchmarks

[View original post](https://x.com/ArtificialAnlys/status/2104578736687653293)
