Skip to content

ComfyUI-StableAudioSampler

Generate audio inside ComfyUI with Stable Audio Open parameters

Visit official site

What ComfyUI-StableAudioSampler is

The plugin is described as an audio sampler integrated into ComfyUI nodes that generates audio and outputs raw bytes and a sample rate. It is open source and under active development for music makers.

What you can do with it

  • Generate audio from HuggingFace loaded models
  • Work with all original Stable Audio Open parameters
  • Get raw bytes and the sample rate as output
  • Save generated audio to a file

Application scenarios

  • Generate distinct rhythms and melodies as a music producer
  • Produce background music for film or games
  • Teach music production in a course

Getting started

  • Set the HF_TOKEN environment variable
  • Download the Stable Audio Open model from HuggingFace
  • Place the model in the proper directory
  • Open ComfyUI and load the plugin

Pros & cons

✓ What we like

  • Raw byte output and sample rate are available
  • Saving audio to a file is supported

! What to watch out for

  • An HF_TOKEN environment variable is needed to load models
  • More sampler options such as gain control and clipping are planned

FAQ

What does the node output?

The material states it generates audio and outputs raw bytes and the sample rate.

What is needed before loading models?

An HF_TOKEN environment variable must be set, and the Stable Audio Open model is downloaded from HuggingFace.

Last reviewed: 2026-11-15

More AI music creation tools

View all →

How we review