We study two foundational problems in audio language models: (1) how to design an audio tokenizer that can serve as an intermediate representation for both understanding and generation; and (2) how to build an audio foundation model that generalizes in few-shot and zero-shot settings, analogous to large language models. To this end, we make the following two contributions. First, we propose ReasoningCodec, a discrete audio codec that factorizes audio into (i) reasoning tokens, which encode text-aligned, high-level analysis and planning representations for audio understanding and hierarchical generation, and (ii) reconstruction tokens, which encode semantic-rich acoustic cues for high-fidelity waveform reconstruction. This design achieves understanding performance comparable to strong continuous representations while improving generation quality and reconstruction fidelity over prior discrete tokenizers. Second, we introduce a unified autoregressive architecture for text and audio, together with multi-stage training and multi-task data construction. Using this framework, we train UniAudio 2.0 on 100B text tokens and 60B audio tokens. Across a wide range of speech, sound, and music tasks, UniAudio 2.0 performs competitively on in-domain evaluations and demonstrates strong few-shot and zero-shot generalization to unseen tasks. Demo, code, and checkpoints will be available at \href{https://dongchaoyang.top/UniAudio2Demo/}{https://dongchaoyang.top/UniAudio2Demo/}.

翻译：本文研究了音频语言模型中的两个基础性问题：（1）如何设计一种既能服务于理解又能服务于生成的音频标记器作为中间表示；（2）如何构建一个能够在少样本和零样本设置下泛化的音频基础模型，类似于大语言模型。为此，我们做出了以下两项贡献。首先，我们提出了ReasoningCodec，一种离散音频编解码器，它将音频因子化为（i）推理标记，用于编码文本对齐的高层分析和规划表示，以支持音频理解和分层生成；以及（ii）重建标记，用于编码富含语义的声学线索，以实现高保真度的波形重建。该设计在实现与强连续表示相当的理解性能的同时，在生成质量和重建保真度上超越了先前的离散标记器。其次，我们引入了一种针对文本和音频的统一自回归架构，并结合了多阶段训练和多任务数据构建。利用该框架，我们在1000亿文本标记和600亿音频标记上训练了UniAudio 2.0。在广泛的语音、声音和音乐任务中，UniAudio 2.0在领域内评估中表现优异，并对未见任务展现出强大的少样本和零样本泛化能力。演示、代码和检查点将在 \href{https://dongchaoyang.top/UniAudio2Demo/}{https://dongchaoyang.top/UniAudio2Demo/} 提供。