IndexTTS2: A Breakthrough in Emotionally Expressive and Duration-Controlled Auto-Regressive Zero-Shot Text-to-Speech
Open paper
Benchmark
Model
Rank
Results
text-to-speech-synthesis-on-seed-tts-test-en
IndexTTS2
–
WER: 1.521
Speaker Similarity: 0.86
text-to-speech-synthesis-on-seed-tts-test-zh
IndexTTS2
–
CER: 1.008
Speaker Similarity: 0.865
Rank counts only results with a code link.