Santiago Valdarrama
@svpino
We now have a benchmark for how often we're tricked into thinking a voice is human.
Here is how they measure this:
You hear two recordings of the same text. One is human, and the other is AI. You need to identify the human.
The best model right now at fooling people: Gemini 3.8 Flash TTS.
I suck at this, by the way. I'm the easiest person in the world to fool.
