Model reference · open weights
stable-audio-open-1.0 is an open-weight audio or speech model from Stability AI. stable-audio-open-1.0 (FP32) weighs 2.6 GB; the smallest configuration that runs it is RTX 3060 12 GB.
Summary of the stabilityai/stable-audio-open-1.0 model card, 2026-10-01
What it is
| Released by | Stability AI |
|---|---|
| Released | 2024-05-24 |
| Parameters | 1.2B |
| VRAM | 2.6 GB for the weights |
What it runs on
| Card | One stream | Memory |
|---|---|---|
| RTX 3060 12 GB | fits | 11.6 GB |
| RTX 4060 Ti 16 GB | fits | 15.4 GB |
| RTX 3090 24 GB | fits | 23.4 GB |
| RTX 4090 24 GB | fits | 23.4 GB |
| RTX 5090 32 GB | fits | 31.0 GB |
| L40S 48 GB | fits | 44.0 GB |
| A100 80 GB | fits | 78.2 GB |
| H100 80 GB | fits | 78.1 GB |
| RTX PRO 6000 Blackwell 96 GB | fits | 93.8 GB |
| DGX Spark (GB10) 128 GB unified | fits | 107 GB |
| H200 141 GB | fits | 138 GB |
| B200 180 GB | fits | 176 GB |
How it works
Running it yourself
Rent a machine by the hour. ComfyUI is installed on it. Open ComfyUI through the tunnel, then Templates → Stable Audio 1.0: Text to Audio: it loads ComfyUI's own build of this model, the files above.
# on your rented machine (the ssh line is on its page in the console)
# get REPO FILE FOLDER: one file into /workspace/models/FOLDER, where ComfyUI loads it from
get() { hf download "$1" "$2" --local-dir /workspace/hf-files && mkdir -p "/workspace/models/$3" && mv "/workspace/hf-files/$2" "/workspace/models/$3/$4"; }
# the files of the template “Stable Audio 1.0: Text to Audio” (5.4 GB)
get Comfy-Org/stable-audio-open-1.0_repackaged stable-audio-open-1.0.safetensors checkpoints
get ComfyUI-Wiki/t5-base t5-base.safetensors text_encoders
start-comfyui# on your computer, in a second terminal: ComfyUI in your browser at http://localhost:8188
# HOST and PORT are your machine's, from its page in the console
ssh -L 8188:localhost:8188 dev@HOST -p PORT