# StepAudio 2.5 技术报告

- 来源：HuggingFace Daily Papers（社区热门论文）
- 发布时间：2026-05-22 08:00
- AIHOT 分数：66
- AIHOT 链接：https://aihot.virxact.com/items/cmpkmzjm808f4sl010szu5zzl
- 原文链接：https://arxiv.org/abs/2605.23463

## AI 摘要

StepAudio 2.5 是一个统一的音频-语言基础模型，能在自动语音识别（ASR）、语音合成（TTS）和实时语音交互三个任务上达到或超越专业系统水平。其核心在于将文本与音频置于共享表示空间，通过数据构建、优化目标和解码约束的差异化设置实现任务专精。该模型的后训练范式以任务定制的强化学习（RLHF）为核心机制，并配合专门的解码策略，将共享主干塑造成三种操作模式：ASR分支提升转录效率；TTS分支实现可控、富有表现力的合成；实时分支则达成低延迟、角色一致的对话。在标准基准测试中，StepAudio 2.5 在三项任务上均取得最优结果，证明单一基础模型能够有效内化语音理解、生成和实时交互的不同部署目标。

## 正文

Unified audio-language modeling has emerged as a prominent trend in modern speech systems, promising to bring the reasoning capabilities of large language models to auditory tasks. However, existing unified foundations often struggle to match the depth of specialized systems across automatic speech recognition (ASR), text-to-speech synthesis (TTS), and realtime spoken interaction. Bridging this gap remains an open challenge. This report presents StepAudio 2.5, a unified audio-language foundation model that matches or exceeds specialized systems across all three capabilities. Rather than treating these tasks as architecturally distinct, we operate on the premise that once text and audio share a multimodal representational space, task specialization becomes a matter of operational regimes: data construction, optimization targets, and decoding constraints. Guided by this insight, we advance the post-training paradigm from standard supervised learning to task-tailored Reinforcement Learning from Human Feedback (RLHF), using it as the primary mechanism to define complex optimization targets. We leverage this RLHF-centric alignment, alongside specialized decoding, to shape a shared backbone into three distinct operational modes. Concretely, the ASR branch advances transcription efficiency via verifiable multi-token decoding; the TTS branch achieves controllable, expressive synthesis through preference-based RLHF and context-rich supervision; and the Realtime branch realizes low-latency, persona-consistent dialogue via generative reward modeling within an RLHF framework. On standard benchmarks, StepAudio 2.5 achieves state-of-the-art results across ASR, TTS, and Realtime, demonstrating that a singular audio-language foundation can successfully internalize the distinct deployment objectives of speech understanding, generation, and live interaction.