Woosh: A Sound Effects Foundation Model

TL;DR

Woosh is a comprehensive sound effects foundation model by Sony AI, offering high-quality audio generation and alignment tools, with competitive performance and accessible code and demos.

Contribution

First open sound effects foundation model with multiple modules, optimized for sound effects, and publicly released with code and demos.

Findings

Competitive performance against existing models like StableAudio-Open and TangoFlux

Includes multiple modules: audio encoder/decoder, text-audio alignment, text-to-audio, video-to-audio

Supports low-resource operation and fast inference

Abstract

The audio research community depends on open generative models as foundational tools for building novel approaches and establishing baselines. In this report, we present Woosh, Sony AI's publicly released sound effect foundation model, detailing its architecture, training process, and an evaluation against other popular open models. Being optimized for sound effects, we provide (1) a high-quality audio encoder/decoder model and (2) a text-audio alignment model for conditioning, together with (3) text-to-audio and (4) video-to-audio generative models. Distilled text-to-audio and video-to-audio models are also included in the release, allowing for low-resource operation and fast inference. Our evaluation on both public and private data shows competitive or better performance for each module when compared to existing open alternatives like StableAudio-Open and TangoFlux. Inference code and model weights are available at https://github.com/SonyResearch/Woosh. Demo samples can be found at https://sonyresearch.github.io/Woosh/.