{"ID":2877760,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.20088","arxiv_id":"2508.20088","title":"AudioStory: Generating Long-Form Narrative Audio with Large Language Models","abstract":"Recent advances in text-to-audio (TTA) generation excel at synthesizing short audio clips but struggle with long-form narrative audio, which requires temporal coherence and compositional reasoning. To address this gap, we propose AudioStory, a unified framework that integrates large language models (LLMs) with TTA systems to generate structured, long-form audio narratives. AudioStory possesses strong instruction-following reasoning generation capabilities. It employs LLMs to decompose complex narrative queries into temporally ordered sub-tasks with contextual cues, enabling coherent scene transitions and emotional tone consistency. AudioStory has two appealing features: (1) Decoupled bridging mechanism: AudioStory disentangles LLM-diffuser collaboration into two specialized components, i.e., a bridging query for intra-event semantic alignment and a residual query for cross-event coherence preservation. (2) End-to-end training: By unifying instruction comprehension and audio generation within a single end-to-end framework, AudioStory eliminates the need for modular training pipelines while enhancing synergy between components. Furthermore, we establish a benchmark AudioStory-10K, encompassing diverse domains such as animated soundscapes and natural sound narratives. Extensive experiments show the superiority of AudioStory on both single-audio generation and narrative audio generation, surpassing prior TTA baselines in both instruction-following ability and audio fidelity. Our code is available at https://github.com/TencentARC/AudioStory","short_abstract":"Recent advances in text-to-audio (TTA) generation excel at synthesizing short audio clips but struggle with long-form narrative audio, which requires temporal coherence and compositional reasoning. To address this gap, we propose AudioStory, a unified framework that integrates large language models (LLMs) with TTA syst...","url_abs":"https://arxiv.org/abs/2508.20088","url_pdf":"https://arxiv.org/pdf/2508.20088v2","authors":"[\"Yuxin Guo\",\"Teng Wang\",\"Yuying Ge\",\"Shijie Ma\",\"Yixiao Ge\",\"Wei Zou\",\"Ying Shan\"]","published":"2025-08-27T17:55:38Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.MM\",\"cs.SD\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false,"code_links":[{"ID":610417,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2877760,"paper_url":"https://arxiv.org/abs/2508.20088","paper_title":"AudioStory: Generating Long-Form Narrative Audio with Large Language Models","repo_url":"https://github.com/TencentARC/AudioStory","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}