Understand this story
On October 31, 2026, Voice Arena launched the Turing TTS benchmark to test whether listeners can distinguish human speech from model speech. The benchmark has listeners choose the human voice from among the same sentence spoken by a human and by a model; the proportion of wrong choices is the Fool Rate, with 50% meaning indistinguishable. According to Rohan Paul, the best-performing model, Gemini 3.8 Flash TTS, made listeners choose wrongly in about 10% of cases; on the Voice Arena preference leaderboard, the top four models are statistically tied, but there is still a clear overall gap relative to humans. There are currently no further developments.
AI-generated from public reports
Latest development · Report
Voice Arena launches the Turing TTS benchmark: the best model fools listeners only about 10% of the timeDevelopments
1 confirmed developments
- Source:Rohan Paul
Reports and discussion timeline
Browse reports and discussion by time. Their evidence levels remain distinct.
Oct 31
Rohan Paul
Voice Arena launches the Turing TTS benchmark: the best model fools listeners only about 10% of the time
Voice Arena has launched the Turing TTS benchmark, in which listeners choose the real human among a real human recording and a model-generated recording of the same sentence; the proportion of wrong choices is the Fool Rate, and 50% means indistinguishable. The best-performing Gemini 3.8 Flash TTS made listeners choose wrongly in about 10% of cases. On Voice Arena's preference leaderboard, the top four models are statistically tied, but overall they still show a clear gap relative to real humans.