Moss_TTS-ComfyUI
ComfyUI nodes for 48 kHz stereo local Transformer TTS with zero-shot voice cloning
About
A set of custom nodes for ComfyUI that implement the MOSS-TTS model for high-fidelity audio generation. It features zero-shot voice cloning, speech continuation, and granular control over duration and pronunciation via markup.
Details
- Built with
- Unknown
- Creator
- Source date
- Published on X Jun 20, 2026
- Listed
- Added to Dropday 2h ago
- Evidence
- Strong
The page is a public GitHub repository containing a complete file structure, installation scripts, and detailed documentation for the custom nodes.
Timeline
Teaser
Video
Playable
Product
Loading…
