xAI's new Grok TTS model has achieved a high score on the Humanness Index, a metric used to evaluate the human-like quality of synthesized speech. In blind voting tests, Grok TTS ranked at the top among various voice models, scoring 96 out of a possible 100, which is only 4 points shy of a genuine human voice. AI
IMPACT Sets a new benchmark for human-like speech synthesis, potentially influencing future voice AI development.
RANK_REASON Frontier-lab model release with system card. [lever_c_demoted from frontier_release: ic=1 ai=1.0]
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
