←Story detail

Trending story

Voice Arena ranks TTS models based on native speakers' votes

1 reports1 story updatesUpdated Oct 24 00:58

Understand this story

AI overview

Voice Arena's TTS leaderboard added five new languages—French, German, Indonesian, Tagalog, and Indian English—and ranks TTS models by having vetted native-speaker listeners blindly listen to two audio samples, vote, and then converting those votes into rankings using Bradley-Terry. According to a report dated October 24, 2026, ElevenLabs ranked first on all five new leaderboards, leading the best models from other vendors by 11 to 26 Elo points; Eleven v4 Turbo topped four of the leaderboards, while on the Indonesian leaderboard Eleven v4 ranked first and Eleven v4 Turbo second. There are currently no subsequent developments.

AI-generated from public reports

Latest development · Report

Voice Arena TTS leaderboard adds five languages, ElevenLabs tops all

Developments

1 confirmed developments

  1. Voice Arena ranks TTS models by native speaker votes

    Source:Rohan Paul

Reports and discussion timeline

Browse reports and discussion by time. Their evidence levels remain distinct.

Oct 24

  1. Rohan Paul

    Voice Arena TTS leaderboard adds five languages, ElevenLabs tops all

    Voice Arena's TTS leaderboard has added five languages: French, German, Indonesian, Tagalog, and Indian English. ElevenLabs ranks first on all five leaderboards, leading the best models from other vendors by 11 to 26 Elo points. Eleven v4 Turbo tops four of the leaderboards, while on the Indonesian leaderboard Eleven v4 ranks first and Eleven v4 Turbo second. The leaderboard uses audited native-speaker blind listening to two audio clips for voting, then converts to rankings using Bradley-Terry.

Related stories

  1. Related storiesArtificial Analysis ranks Phonic 1 first on the Speech to Speech Index
  2. Related storiesGoogle releases world model Genie 4
  3. Related storiesCartesia launches the Managed Agents voice agent platform
  4. Related storiesVoice Arena launches the Turing TTS speech benchmark