Get the latest tech news
PlayAI's new Dialog model achieves 3:1 preference in human evals
February 3, 2025. PlayAI’s Dialog Text-to-Speech model is now in general availability, bringing multilingual capabilities, and exceptional performance
PlayAI’s Dialog Text-to-Speech model is now in general availability, bringing multilingual capabilities, and exceptional performance to applications requiring emotive, human-like speech. Comparing Dialog to ElevenLabs’ Multilingual v2.0 (which has longer latency and would be more suited to applications like dubbing), we tested 60 male and female voice generations using identical text with a panel of 100 respondents. An additional 23 languages are experimental: Afrikaans, Arabic, Bengali, Bulgarian, Croatian, Czech, Danish, Dutch, Greek, Hebrew, Hungarian, Indonesian, Italian, Malay, Polish, Russian, Serbian, Swedish, Tagalog, Thai, Turkish, Ukrainian, and Xhosa.
Or read this on Hacker News
