arxiv:2511.03601

Step-Audio-EditX Technical Report

Published on Nov 5, 2025

· Submitted by

Yang on Nov 5, 2025

StepFun

Upvote

Authors:

Chao Yan ,

Boyong Wu ,

Guoqiang Hu ,

Fei Tian ,

Xuerui Yang ,

Xiangyu Zhang ,

Abstract

Step-Audio-EditX, an open-source LLM-based audio model, excels in expressive and iterative audio editing and zero-shot TTS using large-margin synthetic data.

Generated by Qwen/Qwen2.5-Coder-32B-Instruct

We present Step-Audio-EditX, the first open-source LLM-based audio model excelling at expressive and iterative audio editing encompassing emotion, speaking style, and paralinguistics alongside robust zero-shot text-to-speech (TTS) capabilities.Our core innovation lies in leveraging only large-margin synthetic data, which circumvents the need for embedding-based priors or auxiliary modules. This large-margin learning approach enables both iterative control and high expressivity across voices, and represents a fundamental pivot from the conventional focus on representation-level disentanglement. Evaluation results demonstrate that Step-Audio-EditX surpasses both MiniMax-2.6-hd and Doubao-Seed-TTS-2.0 in emotion editing and other fine-grained control tasks.