Drama 3 scores 94.6% overall on the Artificial Analysis Pronunciation Robustness benchmark, ranking #1 of all models we test, open weights or proprietary.
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.
➤ Expanding Shorthand: 96.6%, ranking #1
➤ Contextually Appropriate: 96.5%, ranking #2, with Gemini 3.8 Flash TTS leading at 97.9%
➤ Preserving Exact Sequences: 87.1%, ranking #3, with HeyGen Voice Turbo leading at 91.8%
➤ Standalone Terms: 91.8%, ranking #13, with Fish Audio Drama 3 Preview leading at 95.9%