AssemblyAI-TTS-1 scores 81.7% overall on the Artificial Analysis Pronunciation Robustness benchmark, ranking #16.
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.
➤ Standalone Terms: 92.4%, ranking #11, with Fish Audio Drama 3 Preview leading at 95.9%
➤ Contextually Appropriate: 90.4%, ranking #16, with Gemini 3.8 Flash TTS leading at 97.9%
➤ Preserving Exact Sequences: 81.5%, ranking #6, with HeyGen Voice Turbo leading at 91.8%
➤ Expanding Shorthand: 73.8%, ranking #17, with Ming-3.0-tts leading at 96.5%