This paper proposes Omni Dense Captioning, a novel task designed to generate continuous, fine-grained, and structured audio-visual narratives with explicit timestamps. To ensure dense semantic coverage, we introduce a six-dimensional structural schema to create "script-like" captions, enabling readers to vividly imagine the video content scene by scene, akin to a cinematographic screenplay. To facilitate research, we construct OmniDCBench, a high-quality, human-annotated benchmark, and propose SodaM, a unified metric that evaluates time-aware detailed descriptions while mitigating scene boundary ambiguity. Furthermore, we construct a training dataset, TimeChatCap-42K, and present TimeChat-Captioner-7B, a strong baseline trained via SFT and GRPO with task-specific rewards. Extensive experiments demonstrate that TimeChat-Captioner-7B achieves state-of-the-art performance, surpassing Gemini-2.5-Pro, while its generated dense descriptions significantly boost downstream capabilities in audio-visual reasoning (DailyOmni and WorldSense) and temporal grounding (Charades-STA). All datasets, models, and code will be made publicly available at https://github.com/yaolinli/TimeChat-Captioner.

翻译：本文提出了全密集描述生成这一新颖任务，旨在生成具有明确时间戳的、连续的、细粒度的且结构化的音视频叙事。为确保密集的语义覆盖，我们引入了一个六维结构模式来创建“类脚本”描述，使读者能够像阅读电影剧本一样，逐场景生动地想象视频内容。为促进研究，我们构建了OmniDCBench，一个高质量的人工标注基准，并提出了SodaM，一种统一的评估指标，该指标在评估时间感知的详细描述的同时，缓解了场景边界模糊性问题。此外，我们构建了一个训练数据集TimeChatCap-42K，并提出了TimeChat-Captioner-7B，这是一个通过SFT和具有任务特定奖励的GRPO训练得到的强基线模型。大量实验表明，TimeChat-Captioner-7B实现了最先进的性能，超越了Gemini-2.5-Pro，同时其生成的密集描述显著提升了在音视频推理（DailyOmni和WorldSense）和时间定位（Charades-STA）方面的下游能力。所有数据集、模型和代码将在 https://github.com/yaolinli/TimeChat-Captioner 公开。