MeloTTS English V3 โ€” GGUF

myshell-ai/MeloTTS English V3 (newest) checkpoint converted to GGUF for CrispASR.

Model Details

  • Architecture: VITS2 (52M params)
  • Output: 44.1 kHz mono PCM
  • Speakers: EN-Newest (0)
  • Symbols: 219 (expanded multilingual set)
  • Tones: 16, Languages: 8
  • Format: F16 GGUF (93 MB)
  • License: MIT

Usage

crispasr -m melotts-en-v3-f16.gguf --tts "Hello world." --tts-output hello.wav
Downloads last month
87
GGUF
Hardware compatibility
Log In to add your hardware

16-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support