Step-Audio: Unified Understanding and Generation in Intelligent Speech Interaction

TL;DR

Step-Audio introduces a comprehensive open-source speech understanding and generation model with advanced control, voice cloning, and task management capabilities, setting new benchmarks in open-source speech AI.

Contribution

It presents the first production-ready open-source unified speech-text model, a generative speech data engine, and an instruction-driven control system, advancing open-source multimodal speech AI.

Findings

Achieves state-of-the-art performance on human evaluations.

Improves open-source benchmark scores by 9.3%.

Demonstrates effective dynamic control and complex task management.

Abstract

Real-time speech interaction, serving as a fundamental interface for human-machine collaboration, holds immense potential. However, current open-source models face limitations such as high costs in voice data collection, weakness in dynamic control, and limited intelligence. To address these challenges, this paper introduces Step-Audio, the first production-ready open-source solution. Key contributions include: 1) a 130B-parameter unified speech-text multi-modal model that achieves unified understanding and generation, with the Step-Audio-Chat version open-sourced; 2) a generative speech data engine that establishes an affordable voice cloning framework and produces the open-sourced lightweight Step-Audio-TTS-3B model through distillation; 3) an instruction-driven fine control system enabling dynamic adjustments across dialects, emotions, singing, and RAP; 4) an enhanced cognitive architecture augmented with tool calling and role-playing abilities to manage complex tasks effectively. Based on our new StepEval-Audio-360 evaluation benchmark, Step-Audio achieves state-of-the-art performance in human evaluations, especially in terms of instruction following. On open-source benchmarks like LLaMA Question, shows 9.3% average performance improvement, demonstrating our commitment to advancing the development of open-source multi-modal language technologies. Our code and models are available at https://github.com/stepfun-ai/Step-Audio.