Artificial Analysis 发布 TTS 发音鲁棒性基准
Announcing the Artificial Analysis Pronunciation Robustness benchmark, measuring how reliably Text t...
AI 导读Artificial Analysis 推出 TTS 发音鲁棒性基准，测试模型能否正确读出难读文本，Google Gemini 3.1 Flash TTS 以 88.1% 居首，SpaceXAI TTS 87.6%、ElevenLabs Eleven v3 85.6% 紧随其后。
来源：Artificial Analysis · x.com