Skip to content
SPECIFICTION
Get listed

Sony Woosh

github.com

WebAPISelf-hosted
Visit github.com
Spec score 6.7 #28 of 29 in AI Sound Effect Generators

Spec sheet

Purpose
Woosh is Sony AI’s publicly released sound effects foundation model, with inference code and open model weights.Read 5 Oct 2026 · github.com
Audience
The repository describes inference scripts, local demos, and an API server for running sound effect generation models.Read 5 Oct 2026 · github.com
API
A self-run API server is provided for inference, but currently supports Woosh-DFlow only.Read 5 Oct 2026 · github.com
Support
The repository welcomes pull requests and asks contributors to open an issue before making major changes.Read 5 Oct 2026 · github.com
Additional models
Release v1.0.1 provides SonicCLAP-AR for audio-text retrieval and SonicCLAP-MOS for alignment with human perceptual judgments.Read 5 Oct 2026 · github.com
Audio models
Woosh-AE provides audio encoding and decoding, while Woosh-CLAP provides text-audio alignment for diffusion conditioning.Read 5 Oct 2026 · github.com
Compute options
Installation instructions offer either CPU or CUDA support.Read 5 Oct 2026 · github.com
Downloads
Pretrained model weights and sample media are available through GitHub releases.Read 5 Oct 2026 · github.com
Inference options
The repository provides installation options with CPU or CUDA support and inference test scripts for each model.Read 5 Oct 2026 · github.com
Licensing
Most repository code is MIT-licensed, code for Woosh-VFlow and Woosh-DVFlow is Apache 2.0 licensed, and released model weights are CC-BY-NC licensed.Read 5 Oct 2026 · github.com
Local demos
The repository includes local Gradio demos for Woosh-Flow and Woosh-DFlow, accessed in a browser on the same machine.Read 5 Oct 2026 · github.com
Model components
The release includes an audio encoder/decoder, a text-audio alignment model, text-to-audio and video-to-audio generators, and distilled versions of the generators.Read 5 Oct 2026 · arxiv.org
Model weights
Open weights for models trained on public datasets are available from the repository’s releases.Read 5 Oct 2026 · github.com
Open weights
The repository provides inference code and open weights for models trained on public datasets.Read 5 Oct 2026 · github.com
Organization
The repository identifies Woosh as a public release of a sound effect foundation model by Sony AI.Read 5 Oct 2026 · github.com
Text-to-audio
Woosh-Flow and Woosh-DFlow generate audio unconditionally or from a text prompt.Read 5 Oct 2026 · github.com
Use case
The models are optimized for sound effects and are presented as tools for audio research and building approaches or baselines.Read 5 Oct 2026 · arxiv.org
Video-to-audio
Woosh-VFlow generates audio from a video sequence and can take optional text prompts.Read 5 Oct 2026 · github.com

Where Specifiction places it

Alternatives to Sony WooshAll alternatives →