MiniMax-Speech: Intrinsic Zero-Shot Text-to-Speech with a Learnable Speaker Encoder
Open paper
Benchmark
Model
Rank
Results
text-to-speech-synthesis-on-seed-tts-test-en
MiniMax-Speech
–
WER: 1.65
Speaker Similarity: 0.692
text-to-speech-synthesis-on-seed-tts-test-zh
MiniMax-Speech
–
CER: 0.83
Speaker Similarity: 0.783
Rank counts only results with a code link.