@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 …
Summary
A new benchmark called Turing TTS measures how often human listeners mistake AI-generated voices for real human speech, with Gemini 3.8 Flash TTS currently the best at fooling people in A/B voice identification tests.
View Cached Full Text
Cached at: 10/30/26, 11:20 PM
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.
Shobhit Banga (@shobhitbanga): Drop 2/15
Are we actually measuring the things we ultimately want our voice AI models to achieve?
The best AI voices are becoming hard to tell apart. From each other. Not from humans.
🚀 Introducing Turing TTS: an evaluation that measures how often human listeners mistake
Similar Articles
@rohanpaul_ai: Voice AI is now good enough that preference and human-likeness can be scored as separate targets. @voicearena_ai launch…
Voice Arena launched Turing TTS, a benchmark that measures how often listeners mistake AI speech for human speech via a 'Fool Rate'; even the best model, Gemini 3.8 Flash TTS, fools listeners only about 10% of the time.
@shobhitbanga: Drop 2/15 Are we actually measuring the things we ultimately want our voice AI models to achieve? The best AI voices ar…
Introducing Turing TTS, an evaluation measuring how often human listeners mistake AI-generated speech for real human speech; even the best TTS models fooled listeners only ~10% of the time, prompting discussion on better metrics for voice AI progress.
@omarsar0: The next breakthrough in voice AI might not be another model taking the #1 spot. It might be a better understanding of …
The next breakthrough in voice AI may come from rethinking how we evaluate models rather than crowning a new top performer, with Voice Arena's Turing TTS benchmark measuring how often human listeners mistake AI voices for real ones.
@_philschmid: https://x.com/_philschmid/status/2103145386542014788
This guide explains how to use Gemini 3.8 TTS to create custom voices by replicating your own or designing new ones, featuring top performance on voice benchmarks.
Is there an uncanny valley for AI voices?
The Bland team explores the uncanny valley effect of AI voices and develops TTS models that can simulate human imperfections to enhance the naturalness and human-like experience of phone interactions.