This workflow uses the MOSS-TTS-v1.5 model (OpenMOSS-Team) to generatehigh-quality Persian (Farsi) speech, patched with 4-bit quantization(via bitsandbytes) so it can run on 8GB VRAM GPUs (e.g. RTX 3060 Ti).The unquantized model (8B params, BF16) normally requires ~16GB VRAM.Built on:- ComfyUI node: comfyui-moss-tts by richservo (github.com/richservo/comfyui-moss-tts)- Model: OpenMOSS-Team/MOSS-TTS-v1.5 (Apache 2.0 license)My contribution: added an optional 4-bit (NF4) quantization option tothe Model Loader node, which the original implementation did notsupport. This patch has also been submitted upstream as a PullRequest to the original repository.⚠️ Disclaimer and Terms of Use:This workflow is shared strictly for educational, research, andentertainment purposes. Any use of it — particularly the voicecloning capability — must be done with the consent of the voice'sowner and in compliance with the laws of the user's country. Pleasedo not use this tool for impersonation, fraud, or any unethical orillegal purpose.The creator of this post assumes no responsibility or liability forany misuse, unethical use, or illegal use of this workflow. Fullresponsibility for how it is used rests entirely with the user.

Persian TTS with MOSS-TTS-v1.5 — 4-bit Quantized for 8GB VRAM GPUs

Initial release: MOSS-TTS-v1.5 workflow patched with optional 4-bit(NF4) quantization to run on 8GB VRAM GPUs.

Files with SHA256: bca2034d039c7f8b12849cbe2d39b39791eac8250dc966db65a1b19fcce81483