Omni2Sound: Towards Unified Video-Text-to-Audio Generation

• URL: http://arxiv.org/abs/2601.02731v2
• Date: Sun, 11 Jan 2026 13:07:34 GMT
• Title: Omni2Sound: Towards Unified Video-Text-to-Audio Generation
• Authors: Yusheng Dai, Zehua Chen, Yuxuan Jiang, Baolong Gao, Qiuhong Ke, Jun Zhu, Jianfei Cai,
• Abstract summary: Training a unified model integrating video-to-audio (V2A), text-to-audio (T2A) and joint video-text-to-audio (VT2A) generation offers significant application flexibility.<n>SoundAtlas is a large-scale dataset (470k pairs) that significantly outperforms existing benchmarks and even human experts in quality.<n>We propose Omni2Sound, a unified VT2A diffusion model supporting flexible input modalities.
• Score: 56.11583645408007
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Training a unified model integrating video-to-audio (V2A), text-to-audio (T2A), and joint video-text-to-audio (VT2A) generation offers significant application flexibility, yet faces two unexplored foundational challenges: (1) the scarcity of high-quality audio captions with tight A-V-T alignment, leading to severe semantic conflict between multimodal conditions, and (2) cross-task and intra-task competition, manifesting as an adverse V2A-T2A performance trade-off and modality bias in the VT2A task. First, to address data scarcity, we introduce SoundAtlas, a large-scale dataset (470k pairs) that significantly outperforms existing benchmarks and even human experts in quality. Powered by a novel agentic pipeline, it integrates Vision-to-Language Compression to mitigate visual bias of MLLMs, a Junior-Senior Agent Handoff for a 5 times cost reduction, and rigorous Post-hoc Filtering to ensure fidelity. Consequently, SoundAtlas delivers semantically rich and temporally detailed captions with tight V-A-T alignment. Second, we propose Omni2Sound, a unified VT2A diffusion model supporting flexible input modalities. To resolve the inherent cross-task and intra-task competition, we design a three-stage multi-task progressive training schedule that converts cross-task competition into joint optimization and mitigates modality bias in the VT2A task, maintaining both audio-visual alignment and off-screen audio generation faithfulness. Finally, we construct VGGSound-Omni, a comprehensive benchmark for unified evaluation, including challenging off-screen tracks. With a standard DiT backbone, Omni2Sound achieves unified SOTA performance across all three tasks within a single model, demonstrating strong generalization across benchmarks with heterogeneous input conditions. The project page is at https://swapforward.github.io/Omni2Sound.

Related papers

• JavisDiT++: Unified Modeling and Optimization for Joint Audio-Video Generation [112.614973927778]
  Joint audio-video generation (JAVG) produces synchronized and semantically aligned sound and vision from textual descriptions.<n>This paper presents JavisDiT++, a framework for unified modeling and optimization of JAVG.<n>Our model achieves state-of-the-art performance merely with around 1M public training entries.
  arXiv  Detail & Related papers  (2026-02-22T12:44:28Z)
• Apollo: Unified Multi-Task Audio-Video Joint Generation [15.004783109205666]
  Non-commercial approaches still suffer audio-visual asynchrony, poor lip-speech alignment, and unimodal degradation.<n>We introduce Apollo and delve into three axes--model architecture, training strategy, and data curation.<n>For datasets, we present the first large-scale audio-video dataset with dense captions.
  arXiv  Detail & Related papers  (2026-01-07T18:03:45Z)
• T2AV-Compass: Towards Unified Evaluation for Text-to-Audio-Video Generation [41.03487954415606]
  Text-to-Audio-Video (T2AV) generation aims to synthesize temporally coherent video and semantically synchronized audio from natural language.<n>We present T2AV-, a unified benchmark for comprehensive evaluation of T2AV systems.<n>Even the strongest models fall substantially short of human-level realism and cross-modal consistency.
  arXiv  Detail & Related papers  (2025-12-24T10:30:35Z)
• ViSAudio: End-to-End Video-Driven Binaural Spatial Audio Generation [55.76423101183408]
  ViSAudio is an end-to-end framework that employs conditional flow matching with a dual-branch audio generation architecture.<n>It generates high-quality audio with spatial immersion that adapts to viewpoint changes, sound-source motion, and diverse acoustic environments.
  arXiv  Detail & Related papers  (2025-12-02T18:56:12Z)
• PrismAudio: Decomposed Chain-of-Thoughts and Multi-dimensional Rewards for Video-to-Audio Generation [57.864929968616586]
  Video-to-Audio (V2A) generation requires balancing four critical perceptual dimensions.<n>We introduce PrismAudio, the first framework to integrate Reinforcement Learning into V2A generation with specialized Chain-of-Thought (CoT) planning.
  arXiv  Detail & Related papers  (2025-11-24T07:11:12Z)
• MultiSoundGen: Video-to-Audio Generation for Multi-Event Scenarios via SlowFast Contrastive Audio-Visual Pretraining and Direct Preference Optimization [10.717164013707693]
  Current video-to-audio (V2A) methods struggle in complex multi-event scenarios.<n>This study proposes a novel V2A framework: MultiSoundGen.<n>It introduces direct preference optimization (DPO) into the V2A domain.
  arXiv  Detail & Related papers  (2025-09-24T11:04:34Z)
• AudioGen-Omni: A Unified Multimodal Diffusion Transformer for Video-Synchronized Audio, Speech, and Song Generation [24.799628787198397]
  AudioGen- Omni generates high-fidelity audio, speech, and song coherently synchronized with the input video.<n>Joint training paradigm integrates large-scale video-text-audio corpora.<n>Dense frame-level representations are fused using an AdaLN-based joint attention mechanism.<n>With an inference time of 1.91 seconds for 8 seconds of audio, it offers substantial improvements in both efficiency and generality.
  arXiv  Detail & Related papers  (2025-08-01T16:03:57Z)
• Nexus: An Omni-Perceptive And -Interactive Model for Language, Audio, And Vision [83.0622534215881]
  This work proposes an industry-level omni-modal large language model (LLM) pipeline that integrates auditory, visual, and linguistic modalities.<n>Our pipeline consists of three main components: First, a modular framework enabling flexible configuration of various encoder-LLM-decoder architectures.<n>Second, a lightweight training strategy that pre-trains audio-language alignment on the state-of-the-art vision-language model Qwen2.5-VL.<n>Third, an audio synthesis pipeline that generates high-quality audio-text data from diverse real-world scenarios.
  arXiv  Detail & Related papers  (2025-02-26T17:26:36Z)
• YingSound: Video-Guided Sound Effects Generation with Multi-modal Chain-of-Thought Controls [10.429203168607147]
  YingSound is a foundation model designed for video-guided sound generation.<n>It supports high-quality audio generation in few-shot settings.<n>We show that YingSound effectively generates high-quality synchronized sounds through automated evaluations and human studies.
  arXiv  Detail & Related papers  (2024-12-12T10:55:57Z)
• Frieren: Efficient Video-to-Audio Generation Network with Rectified Flow Matching [51.70360630470263]
  Video-to-audio (V2A) generation aims to synthesize content-matching audio from silent video.<n>We propose Frieren, a V2A model based on rectified flow matching.<n>Experiments indicate that Frieren achieves state-of-the-art performance in both generation quality and temporal alignment.
  arXiv  Detail & Related papers  (2024-06-01T06:40:22Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.