HeyGen Voice tops Artificial Analysis’s Controlled Voice TTS Arena leaderboard

Artificial Analysis says its Controlled Voice Arena evaluates text-to-speech models using the same eight cloned voices across US and UK English. HeyGen Voice led with an Elo of 1,201 across 1,468 appearances, ahead of Qwen-Audio-3.1-TTS-Plus at 1,182 and Eleven v4 Turbo at 1,166. It scored 83.1% on a separate pronunciation robustness benchmark, ranking 10th of 29 models, and is priced at $30 per million characters.