Pronunciation Robustness measures whether Text to Speech models correctly pronounce challenging text across four categories, with human reviewers judging each clip against pre-agreed accepted pronunciations. Ming-3.0-tts leads overall at 93.2%.
➤ Expanding Shorthand: Ming-3.0-tts ranks #1 at 96.5%, ahead of Eleven v4 at 94.1% and Drama 3 Preview at 93.6%.
➤ Preserving Exact Sequences: Ming-3.0-tts ranks #1 at 90.6%, ahead of Drama 3 Preview at 86.3% and SpaceXAI TTS at 85.7%.
➤ Contextually Appropriate: Ming-3.0-tts scores 91.0%, with Gemini 3.8 Flash TTS leading at 97.9%.
➤ Standalone Terms: Ming-3.0-tts scores 88.5%, with Drama 3 Preview leading at 95.9%.
