Gemini 3.8 Flash TTS 登顶 Artificial Analysis 发音鲁棒性基准
语音合成圈的榜单更新了，Gemini 3.8 Flash TTS 发音准确率干到 89.5%，不过序列和术语两项分别被 SpaceXAI 和 Qwen 的模型拿走，各家各有强项。
Google 的 Gemini 3.8 Flash TTS 在 Artificial Analysis 发音鲁棒性基准上以 89.5% 排名第一，超过 Gemini 3.1 Flash TTS 的 88.2% 和 SpaceXAI TTS 的 87.6%。它在 Contextually Appropriate 发音上拿到 97.9%，缩写扩展得分为 86.1%，两项均居首位。不过 SpaceXAI TTS 在保留精确序列一项以 85.7% 领先，Qwen-Audio-3.0-TTS-Plus 在独立术语上以 95.5% 拿下第一。
Gemini 3.8 Flash TTS takes the #1 spot on the Artificial Analysis Pronunciation Robustness benchmark at 89.5%, ahead of Gemini 3.1 Flash TTS at 88.2%, SpaceXAI TTS at 87.6%, and Gemini 3.8 Flash-Lite TTS at 87.4%.
Gemini 3.8 Flash TTS leads on Contextually Appropriate pronunciation at 97.9% and Expanding Shorthand at 86.1%, while SpaceXAI TTS leads on Preserving Exact Sequences at 85.7% and Qwen-Audio-3.0-TTS-Plus leads on Standalone Terms at 95.5%.
Listen to examples from our Pronunciation Robustness benchmark below ⬇️
