ZipVoice matches the quality of much larger zero-shot text-to-speech models while using 123M parameters and as few as 4 sampling steps.
Neural codec language models are zero-shot text to speech synthesizers,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.AS 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
ZipVoice: Fast and High-Quality Zero-Shot Text-to-Speech with Flow Matching
ZipVoice matches the quality of much larger zero-shot text-to-speech models while using 123M parameters and as few as 4 sampling steps.