SAO-Instruct: Free-form Audio Editing using Natural Language Instructions
This addresses the need for flexible audio editing tools for users in creative or multimedia fields, though it is incremental as it builds on existing generative models.
The paper tackles the problem of editing existing audio using free-form natural language instructions, which was previously underexplored, and introduces SAO-Instruct, a model that achieves competitive performance on objective metrics and outperforms other approaches in a subjective listening study.
Generative models have made significant progress in synthesizing high-fidelity audio from short textual descriptions. However, editing existing audio using natural language has remained largely underexplored. Current approaches either require the complete description of the edited audio or are constrained to predefined edit instructions that lack flexibility. In this work, we introduce SAO-Instruct, a model based on Stable Audio Open capable of editing audio clips using any free-form natural language instruction. To train our model, we create a dataset of audio editing triplets (input audio, edit instruction, output audio) using Prompt-to-Prompt, DDPM inversion, and a manual editing pipeline. Although partially trained on synthetic data, our model generalizes well to real in-the-wild audio clips and unseen edit instructions. We demonstrate that SAO-Instruct achieves competitive performance on objective metrics and outperforms other audio editing approaches in a subjective listening study. To encourage future research, we release our code and model weights.