Askable Labs has launched VOICE-H, a benchmark for evaluating AI-generated speech against human recordings, finding that listeners preferred emotional fit over human likeness. The study compared nine text-to-speech models with original human recordings in nearly 4,500 blind comparisons, using 100 clips selected from more than 40,000 real interviews. A total of 300 participants in Australia, New Zealand, the United Kingdom and the United States each completed 15 randomised head-to-head tests. Google's Gemini 3.1 Flash Voice ranked first overall with an Elo score of 1101, ahead of the human recording on 1045 and Cartesia's Sonic 3.5 on 1041. Gemini also led the individual categories for naturalness, accuracy, and emotion and tone. Human speech ranked second for naturalness with a score of 1062 to 1094, but fell to eighth for accuracy on 947. The widest gap appeared in emotion and tone, where Gemini scored 1146, more than 110 Elo points ahead of the human recording on 1034. The most common complaint was that voices sounded robotic, drawing 590 negative mentions. One model's pauses and filler words drew 52 complaints and no positive mentions, contributing to 41 lost votes. VOICE-H collected written explanations for every choice, creating a qualitative dataset alongside pairwise comparisons. John Goleby, Chief Executive Officer of Askable Labs, said findings challenge the assumption that realism is the