yl4579 / StyleTTS2

StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Models
MIT License
4.78k stars 391 forks source link

Speech conditioning like tortoise TTS #246

Open NikitaKononov opened 3 months ago

NikitaKononov commented 3 months ago

Hello, thank for sharing your awesome work Can you please tell me, if there's an ability to to TTS with your model with speech conditioning? Zero-shot tts the way tortoise tts or xtts does that As I get it from the code, it can synthesize speech only in VITS manner - with speaker number Am I wrong? thank you

platform-kit commented 3 months ago

It includes zero shot capabilities. https://replicate.com/adirik/styletts2