AI 导读
我通常会划过那些基准测试的帖子，因为是自报数据。 这个不是：Voice Arena 自己测量每一个模型并公布原始数字。 Gradium 以 231 ms 拿下最快首音频时间。 这确实有意义。 恭喜 Gradium 团队！
正文
I usually scroll past benchmark posts because they're self-reported.
This one isn't: Voice Arena measures every model themselves and publishes the raw numbers.
Gradium earns fastest time-to-first-audio at 231 ms.
This actually means something.
Congrats to the Gradium team! https://t.co/AIpbUyGIPu https://t.co/KJU2F2gMjR
来源：@rohanpaul_ai · x.com