TTS leaderboard: xAI hits 87.6% pronunciation accuracy, Kokoro 82M fastest at 242 chars/s

ArtificialAnlys · x · 2026-09-22

Artificial Analysis launched a full Text-to-Speech model comparison covering Arena Elo, speed, price, and a new Pronunciation Robustness metric (human-judged correctness of English spans), ranking 27 of 93 models. Key numbers: xAI TTS scores 87.6% accuracy at 106 chars/s; Realtime TTS-2 Flash hits 77.8% at 220 chars/s; open-source Kokoro 82M v1.0 is fastest at 242 chars/s but scores just 55.5%.

Related event: Artificial Analysis Launches TTS Pronunciation Robustness Benchmark; Gemini 3.8 Flash TTS Tops at 89.5%(12 posts)→

Original post →

More from Models

• Opus 5.5 feels nerfed — user blames system prompt restrictions, not the model — oyacaro · 2026-11-12
• Grok Bot now auto-detects and blocks prompt injection hidden in web pages — heypearlai · 2026-11-12
• ChatGPT now links to brand homepages far more, reshaping brand-mention tracking — lilyraynyc · 2026-11-12
• YC-backed Monte launches post-training platform to build proprietary models from your agents' real work — ycombinator · 2026-11-12
• Leak Claims OpenAI Will Launch Entire GPT-6.2 Family Tomorrow to Counter Opus 5.5 and Fable 5.2 — heypearlai · 2026-11-12
• ARC-AGI-3 leaderboard: models score 90%+ but at $10K+ per task — haider1 · 2026-11-12

Models channel →