ThinkSound: Chain-of-Thought Reasoning in Multimodal LLMs for Audio Generation and Editing

Huadai Liu, Kaicheng Luo, Jialei Wang, Wen Wang, Qian Chen, Zhou Zhao, Wei Xue

Keywords: Any-to-Audio Generation, Chain-of-thought, Multimodal Large Language Model

TL;DR: we introduce ThinkSound, a framework that utilizes Chain-of-Thought reasoning to systematically break down audio generation for videos into a step-by-step interactive process.

Abstract: While end-to-end video-to-audio generation has greatly improved, producing high-fidelity audio that authentically captures the nuances of visual content remains challenging. Like professionals in the creative industries, this generation requires sophisticated reasoning about items such as visual dynamics, acoustic environments, and temporal relationships. We present **ThinkSound**, a novel framework that leverages Chain-of-Thought (CoT) reasoning to enable stepwise, interactive audio generation and editing for videos. Our approach decomposes the process into three complementary stages: foundational foley generation that creates semantically coherent soundscapes, interactive object-centric refinement through precise user interactions, and targeted editing guided by natural language instructions. At each stage, a multimodal large language model generates contextually aligned CoT reasoning that guides a unified audio foundation model. Furthermore, we introduce **AudioCoT**, a comprehensive dataset with structured reasoning annotations that establishes connections between visual content, textual descriptions, and sound synthesis. Experiments demonstrate that ThinkSound achieves state-of-the-art performance in video-to-audio generation across both audio metrics and CoT metrics, and excels in the out-of-distribution Movie Gen Audio benchmark. The project page is available at https://ThinkSound-Project.github.io.

Primary Area: Applications (e.g., vision, language, speech and audio, Creative AI)

Submission Number: 3394