MOSS-TTS (OpenMOSS) โ€” GGUF

GGUF weights for MOSS-TTS-Delay (text-to-speech / voice cloning), converted for use with openmoss โ€” a standalone C++/GGML runtime (CUDA + Vulkan), and with Lemonade as a GGML media backend.

Source model: https://huggingface.co/OpenMOSS-Team/MOSS-TTS License: see the source model.

Files

moss-tts-1.5-q8_0.gguf (Q8 backbone, recommended) and moss-tts-1.5.gguf (f16, reference), each with its *.extras.gguf sidecar (audio embeddings + heads + codec).

Downloads last month
439
GGUF
Model size
2B params
Architecture
moss_tts_delay
Hardware compatibility
Log In to add your hardware

8-bit

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