> ## Documentation Index
> Fetch the complete documentation index at: https://docs.comfy.org/llms.txt
> Use this file to discover all available pages before exploring further.

# Stable Audio audio generation model (stability/stable-audio): where to run it

> Stable Audio is a audio generation model from Stability AI. Run it with ComfyUI locally and Comfy Cloud; templates, files, nodes, and pricing.

Model ID: stability/stable-audio
Provider: stability
Product: local, cloud, workflows
Input: text
Output: audio
License: open-weights

Stable Audio is a audio generation model from Stability AI. It takes text as input and produces audio. It has open weights, so you can download the files and run it locally in ComfyUI.

## Where you can run it

| Where | Page | Use it when |
| - | - | - |
| ComfyUI (local or Comfy Cloud) | [Stable Audio 1.0 in ComfyUI: Text to Audio Workflow](https://docs.comfy.org/tutorials/audio/stable-audio/stable-audio-1.md) | You follow a step-by-step workflow tutorial |
| ComfyUI (local or Comfy Cloud) | [Stable Audio 3 ComfyUI workflow example](https://docs.comfy.org/tutorials/audio/stable-audio/stable-audio-3.md) | You follow a step-by-step workflow tutorial |
| Comfy Cloud | [Open `audio_stable_audio_3_medium` on Comfy Cloud](https://cloud.comfy.org/?template=audio_stable_audio_3_medium) | You want to run a ready-made workflow without installing anything |

## Model files for running it locally

Put each file in the matching folder under `ComfyUI/models/`. These come from the workflow templates below (workflow\_templates at `3c2199b9`).

| File | Folder | Download |
| - | - | - |
| `stable_audio_3_medium_base.safetensors` | `models/checkpoints/` | [Download](https://huggingface.co/Comfy-Org/stable-audio-3/resolve/main/checkpoints/stable_audio_3_medium_base.safetensors) |
| `stable_audio_3_medium.safetensors` | `models/checkpoints/` | [Download](https://huggingface.co/Comfy-Org/stable-audio-3/resolve/main/checkpoints/stable_audio_3_medium.safetensors) |
| `stable-audio-open-1.0.safetensors` | `models/checkpoints/` | [Download](https://huggingface.co/Comfy-Org/stable-audio-open-1.0_repackaged/resolve/main/stable-audio-open-1.0.safetensors) |
| `qwen3.5_2b_bf16.safetensors` | `models/text_encoders/` | [Download](https://huggingface.co/Comfy-Org/Qwen3.5/resolve/main/text_encoders/qwen3.5_2b_bf16.safetensors) |
| `t5gemma_b_b_ul2.safetensors` | `models/text_encoders/` | [Download](https://huggingface.co/Comfy-Org/stable-audio-3/resolve/main/text_encoders/t5gemma_b_b_ul2.safetensors) |
| `t5-base.safetensors` | `models/text_encoders/` | [Download](https://huggingface.co/ComfyUI-Wiki/t5-base/resolve/main/t5-base.safetensors) |

## Workflow templates

| Template | Title | Added |
| - | - | - |
| `audio_stable_audio_3_medium_base` | Stable Audio 3.0 Medium Base | 2026-05-20 |
| `audio_stable_audio_3_medium` | Stable Audio 3.0 Medium | 2026-05-20 |
| `audio_stable_audio_example` | Stable Audio 1.0: Text to Audio | 2025-03-01 |


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.