Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens
Open paper
Benchmark
Model
Rank
Results
text-to-speech-synthesis-on-seed-tts-test-en
Spark-TTS
#12
WER: 1.98
Speaker Similarity: 0.584
text-to-speech-synthesis-on-seed-tts-test-zh
Spark-TTS
#22
Speaker Similarity: 0.672
Rank counts only results with a code link.