PulpCut/Stable-Audio-3-Small-SFX-safetensors

Stable Audio 3 Small SFX — safetensors

Powered by Stability AI.

This is Stability AI's Stable Audio 3 Small SFX repackaged into safetensors for H3ddle, an open-source native macOS app that generates audio locally on Apple Silicon.

Nothing about the model was changed. Tensor names, shapes and values are identical to the source; only the container differs. No retraining, merging, pruning or quantization was performed.

Why this exists

Stability publishes these weights twice: as fp32 in the gated stable-audio-3-small-sfx repository, and as f16 NumPy archives in the ungated stable-audio-3-optimized repository. This repackages the second, because it needs no Hugging Face account and is half the size. The encoder half of the autoencoder is omitted: text-to-audio never runs it, and leaving it out saves 215 MB.

Safetensors is what the consuming engine already reads, so this avoids teaching an installer to parse .npz.

Contents

file	what it is
dit.safetensors	the 20-block diffusion transformer, f16
text_encoder.safetensors	T5Gemma encoder, f16
decoder.safetensors	SAME-S audio decoder, f32 as released
tokenizer.json	Hugging Face fast-tokenizer form
tokenizer.model	the original SentencePiece model

The text encoder's architecture travels in the safetensors metadata under config, where it shipped as a JSON blob in the source archive.

Licence

The model is licensed under the Stability AI Community License, Copyright © Stability AI Ltd. All Rights Reserved. It is free for research and non-commercial use, and for commercial use below USD $1M in annual revenue after registering with Stability AI. See NOTICE for the required attribution and a statement of the modifications made here.

The text encoder is T5Gemma, provided under and subject to the Gemma Terms of Use; see LICENSE_GEMMA.md.

Outputs may not be used to train competing foundational generative models.