MOSS-SoundEffect_v2.0_MPS_ROCm

VladimirTalyzin/MOSS-SoundEffect_v2.0_MPS_ROCm

★ 0 stars Python API Integration Updated today

Desktop app for the MOSS-SoundEffect-v2.0 text-to-audio diffusion model, with working AMD ROCm (Windows) and Apple Silicon (MPS) support. No API keys, no browser. Includes CLI, benchmark tools and an MCP server.

View on GitHub → 🔍 Audit Wallet Slippage →

Quick Install

Copy the config for your editor. Some servers may need additional setup — check the README.

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "moss-soundeffect_v2.": {
      "command": "uvx",
      "args": [
        "moss-soundeffect-v2.0-mps-rocm"
      ]
    }
  }
}

Or install with pip: pip install moss-soundeffect-v2.0-mps-rocm

README Excerpt

A small, dependency-light desktop front-end for the text-to-audio diffusion model from the OpenMOSS team. Type a description, get a sound effect. Everything runs locally — no API keys, no uploads. The upstream project ships CUDA-oriented scripts and a Gradio demo. This repository adds what was missing for the hardware I actually use: a native

Tools (14)

MOSS_CPU_VAEMOSS_DEVICEMOSS_DTYPETORCH_ROCM_AOTRITON_ENABLE_EXPERIMENTALcfgcpucudaformatgenerate_sound_effectmpspromptsecondsseedsteps

Topics

amd-gpuapple-silicondesktop-appdiffusion-modelmcp-servermpspytorchrocmsound-effectstext-to-audiotkinter

MOSS-SoundEffect_v2.0_MPS_ROCm

Quick Install

README Excerpt

Tools (14)

Topics

Related API Integration Servers