AI 导读
Gemini 3.8 Flash TTS 每秒处理 44.1 个字符，而 Gemini 3.8 Flash-Lite TTS 为每秒 40.2 个字符，分别约为实时的 2.7 倍和 2.4 倍。 这两款模型仍落后于我们追踪的更快 Text to Speech 模型，例如 Falcon 2 的每秒 204.9 个字符和 Luna TTS 的每秒 153.5 个字符。
正文
Gemini 3.8 Flash TTS processes 44.1 characters per second, compared to 40.2 characters per second for Gemini 3.8 Flash-Lite TTS, approximately 2.7x and 2.4x faster than realtime, respectively.
Both models remain behind faster Text to Speech models we track, such as Falcon 2 at 204.9 characters per second and Luna TTS at 153.5 characters per second.
来源：@ArtificialAnlys · x.com