Hugging Face has launched the Open TTS Leaderboard, which evaluates multilingual text-to-speech and voice cloning models using objective metrics rather than human votes. The Hugging Face Hub hosts more than 8K TTS models as of Sep 30, 2026, yet only 16 of 92 models on Artificial Analysis are open-weights. The leaderboard measures intelligibility via WER/CER with Qwen3 ASR, speed via RTFx and time-to-first-audio, and speaker similarity via WavLM embeddings, plus multilingual rankings and a listening tab.
No score is assigned. Sources and their independence are shown in the citation chain below.