MaskGCT: Zero-Shot Text-to-Speech with Masked Generative Codec Transformer
Paper
•
2409.00750
•
Published
•
3
TTS models that support zero-shot voice cloning
Note https://github.com/yl4579/StyleTTS-ZS (Official code not released yet, still under development)
Note Unofficial implementation: https://github.com/lucidrains/e2-tts-pytorch