We present EchoWM, an omnimodal world model for enterable generative media that responds to continuous navigation while jointly generating 720p video, environmental sound, music and speech. We organize interaction around camera intent: in first-person scenes, it specifies observer motion, while in third-person scenes, camera--character dynamics are learned from data without view-specific controllers. Discrete commands and continuous poses are mapped to a shared metric-scale relative 6-DoF trajectory, with dataset-level calibration preserving motion magnitude across heterogeneous data. To jointly learn audio-visual generation and trajectory control, we construct a complementary data engine and adopt progressive training followed by autoregressive post-training for long-horizon generation. Extensive evaluations show that \model achieves strong trajectory following and high visual quality on public world-model benchmarks, supporting both first- and third-person interaction across varied subjects, and maintaining synchronized environmental sound and speech over long-horizon generation.
Recent advances in generative video modeling have enabled diverse generation, reference-based synthesis, extension, and editing, but existing approaches often rely on fragmented task-specific models. A general model must distinguish heterogeneous target, source, and reference signals to determine what to generate, preserve, or use as guidance, while reducing interference among tasks. Joint audio-visual generation further increases this challenge by introducing diverse conditioning and output configurations across modalities. We present Vorch-Omni, a unified multi-task framework for audio-visual synthesis based on an arbitrary-condition-to-arbitrary-output formulation. It flexibly treats video and audio signals as either conditioning inputs or generation targets. Token-level conditioning masks and task identifiers distinguish targets, source content, and references, while position types separate temporal context from independent conditions. To capture semantic and structural information, Vorch-Omni employs complementary visual conditioning pathways: a vision-language model interprets sampled frames with text instructions, and a video VAE encodes conditions into latent tokens for direct guidance. We further build a distributed data pipeline to curate diverse temporally aligned audio-visual clips, generate structured captions and metadata, and balance heterogeneous task distributions. Built on a single flow-matching diffusion transformer without task-specific architectural changes, Vorch-Omni supports over 10 tasks, including text-to-video, text-to-audio-video, image- and reference-conditioned generation, temporal extension, audio-driven generation, video transformation, and audio-visual editing. This unified framework provides a scalable foundation for general-purpose audio-visual generation and manipulation.
Andrey Shutkin, Denis Parkhomenko, Ivan Kirillov +11cs.CV cs.LG cs.SD
Latent diffusion modeling (LDM), a prominent paradigm, utilizes tokenizers to map input signal to compressed representation. This dependency positions tokenizer as an integral part of generation process itself, since it affects learning speed, quality of synthesized samples and lay foundation for later applications. This report presents series of KVAE tokenizers for audio, image and video, all designed for subsequent text-conditioned generation: KVAE-Audio, a continuous full-band 48 kHz tokenizer with a 50 Hz latent of 64 channels; KVAE-3D -- two causal video tokenizers for 4x16x16 and 4x8x8 compression; KVAE-2D, an image model, compressing input by factor of 8 with 32 channels. We demonstrate that reconstruction (PSNR, LPIPS, PESQ, etc.) and generation results on objective (Frechet Distance, CLIP score, CLAP score, etc.) and subjective (side-by-side evaluation) metrics matches or surpasses frontier opensource tokenizers, such as VAEs from Wan-2.2, HunyuanVideo-1.5, FLUX.2, MovieGen, StableAudio and MMAudio. Considering difficulty of development, we share with community training details, model selection method and ablation on design choices. The code is publicly available at https://github.com/kandinskylab/kvae and https://github.com/kandinskylab/kvae-audio.
3D Gaussian Splatting (3DGS) turns captured or generated imagery into photorealistic 3D world simulations that users can freely explore, yet these worlds remain silent. Because existing audio generation methods condition on a single image or viewpoint, their sound is tied to that observation and cannot stay consistent while a listener moves. We introduce the task of generating a spatially consistent soundscape for a given 3DGS world through auditory grounding, identifying which objects in the world should emit sound and anchoring each to a persistent 3D position, and present Scene2Sound, a training-free framework built on this grounding. From the input world alone, our pipeline selects viewpoints that jointly cover the scene, identifies sound-emitting objects with a vision-language model, and associates the multi-view detections into 3D instances through Gaussian set matching, which measures the overlap between the Gaussian sets that render each detection. Each source then receives generated audio that a standard object-based audio engine spatializes in real time at arbitrary listener poses. We further propose two spatial-consistency metrics, one testing whether rendered audio responds consistently to listener motion and one testing whether the claimed sources are supported by views held out from their placement. On a curated set of generated 3DGS worlds and on 3DGS scenes generated from real-world 360-degree captures, Scene2Sound preserves the audio quality of strong per-viewpoint baselines while remaining spatially consistent where per-viewpoint and single-panorama pipelines do not, and a user study confirms the perceptual benefit. Project page: https://masaki-lmd.github.io/scene2sound/.
Unified audio models capable of audio understanding, audio generation and, increasingly, audio editing are proliferating rapidly. Yet a basic question about them remains unanswered: do the two heads of a unified model agree about the same audio? Current practice evaluates each capability in isolation on specialized benchmarks, and never asks whether a model can make sense of its own generations. We present TORUS, the first self-coherence test for audio-native unified models. TORUS comprises 48 three-stage self-coherence tests carrying 432 six-option questions spanning speech, sound and music across five task families. We holistically evaluate five open unified models alongside a Cascaded Baseline that combines state-of-the-art specialized generation, editing and understanding models. The best unified model answers 50.5% of questions against the Cascaded Baseline's 63.2% and a 16.7% chance floor. Models struggle on audio editing. Among the evaluated audio models (specialized and unified), we observe limited self-coherence, and thus position self-coherence as an essential test for future audio systems.
Wei-Jaw Lee, Hsuan-Yu Yeh, Ting-Yi Hu +3cs.SD cs.AI eess.AS
Cover song generation (CSG) should preserve the melodic and linguistic content of a reference song while recreating the remaining musical components. The state-of-the-art model SongEcho utilizes $F_0$ sequences and voiced/unvoiced (V/UV) tags for conditioning; however, implicit linguistic information from V/UV tags cannot guarantee lyric accuracy, leading to a high phoneme error rate (PER). Inspired by singing voice synthesis (SVS), we propose MPEcho, which integrates a phoneme encoder and a length regulator (LR) into the SongEcho framework. By providing explicit phoneme-level conditioning and precise temporal boundaries, MPEcho significantly reduces PER. To enable this, we developed Phonsa, a Whisper-based automatic transcription model that provides high-precision phoneme-level annotations for singing voices, overcoming the scarcity of high-quality audio-phoneme pairs. Experimental results validate the effectiveness of Phonsa for alignment and MPEcho for end-to-end CSG. The audio samples, code and weights can be accessed from https://lonian6.github.io/MPEcho.github.io/.
Ali Boudaghi, Hadi Zarecs.SD cs.LG eess.AS eess.SP math.NA
Zero-shot text-guided editing of real-world music recordings requires balancing semantic modification with faithful preservation of the original musical structure. Although recent diffusion transformers trained with rectified flow have achieved remarkable success in text-to-music generation, extending them to edit existing recordings remains challenging because editing requires accurate deterministic inversion, reliable structural preservation, and numerically stable integration throughout the inversion and generation processes. We present FlowSonic, a zero-shot music editing framework built upon a pretrained diffusion transformer trained with rectified flow. FlowSonic first deterministically inverts a real-world recording into the latent space and preserves its musical structure during editing by reusing cross-attention representations extracted during inversion. To improve the numerical reliability of inversion-based editing, we introduce a high-order ODE solver and systematically investigate how different numerical integration schemes influence trajectory stability, structural preservation, and semantic controllability. Comprehensive experiments on timbre-transfer and genre-modification tasks demonstrate that FlowSonic consistently outperforms existing music editing methods across semantic alignment, harmonic preservation, structural consistency, and perceptual audio quality. We further provide geometric and empirical analyses showing how the proposed numerical integration strategy improves latent trajectory stability and leads to more reliable music editing.
Audio intelligence involves understanding, reasoning about, and generating both audio and speech. In this work, we introduce Nemotron-Labs-Audex-30B-A3B (Audex), a unified audio-text LLM built on Nemotron-Cascade-2-30B-A3B, a strong text-only MoE LLM. Audex adopts a simple unified design with a single Transformer decoder: audio inputs are encoded and projected into the text embedding space, while text tokens and quantized audio output tokens are treated uniformly during generation. This architecture enables strong audio-text fusion, seamless multimodal generation, and compatibility with standard LLM training and inference infrastructure. For training, we meticulously curate audio-text datasets comprising 157.4B audio tokens and 320.5B text tokens. We apply multi-stage supervised training on these datasets, followed by text-only Cascade RL and multi-domain on-policy distillation. Audex delivers state-of-the-art audio understanding, speech recognition and translation, text-to-speech, audio generation, and speech-to-speech generation, while preserving very compelling reasoning, alignment, knowledge, long-context, and agentic capabilities of its text-only LLM backbone with marginal or no regression. We release the model checkpoints to facilitate open research.
Michael Finkelson, Daniel Segal, Eitan Richardson +7cs.SD cs.AI cs.CV
Existing multi-speaker dialogue systems bind speakers to utterances through structured supervision: per-turn tags, multi-stream transcriptions, or learnable speaker embeddings. These systems operate within speech-only pipelines that produce clean vocal sequences without the ambient texture of real conversations. We take a different approach. Our method, ScenA, conditions a text-to-audio flow-matching foundation model, pretrained on large-scale in-the-wild data, directly on multiple reference voices and a free-form natural language prompt that describes an entire multi-speaker audio scene. Leveraging such a foundational model allows us to inherit its capacity for natural, non-studio audio: background noise, room acoustics, overlapping dialogue, and spontaneous paralinguistic events, while adding multi-speaker control without any per-turn structure. Concretely, reference latents are concatenated into the model's token sequence and distinguished by lightweight identity-aware positional encodings. However, we identify a critical obstacle to this approach: the \textit{Reference Shortcut}. During training under standard noise schedules, the model can identify the matching reference by acoustic similarity to the noisy target, bypassing the text prompt entirely. We address this with a high-noise-biased timestep distribution that forces the model to rely on the text prompt for speaker assignment. We evaluate ScenA on the CoVoMix2-Dialogue benchmark, showing that it outperforms existing multi-speaker systems on speaker-binding metrics while generating rich conversational audio with overlapping speech, emotional vocalizations, and ambient sound. Our results demonstrate the advantage of using a general-purpose audio model conditioned on a free-form scene description, rather than passing structured dialog scripts through a speech-only pipeline.
We present FoleyGenEx, a unified video-to-audio (VTA) framework integrating multi-modal control, frame-level temporal alignment, and fine-grained semantics, enabling synchronized, versatile audio synthesis for diverse tasks. Existing VTA methods either have multi-modal control but weak temporal alignment or strong alignment but lack reference audio conditioning and semantic precision. FoleyGenEx fills this gap via three core innovations: a conditional injection mechanism for audio-controlled VTA and Foley extension, a multi-modal dynamic masking strategy preserving training synchronization, and an adverb-based data augmentation algorithm leveraging signal processing and large language models to enhance textual supervision with nuanced semantics. Experiments on AudioCaps, VGGSound, and Greatest Hits demonstrate its competitive controllable VTA performance against existing methods. Demo samples are available at https://foleygenex.github.io/FoleyGenEx.
Zeyue Tian, Lei Ke, Zhaoyang Liu +8cs.SD cs.CV cs.MM
Audio and music generation based on flexible multimodal control signals is a widely applicable topic, with the following key challenges: 1) a unified multimodal modeling framework, 2) large-scale, high-quality training data, and 3) the prohibitive inference cost of multi-step diffusion sampling. As such, we propose AudioX-Turbo, a unified and efficient framework for anything-to-audio generation that integrates varied multimodal conditions (i.e., text, video, and audio signals) in this work. AudioX-Turbo follows a teacher-student paradigm. The teacher AudioX-Base is built on a Multimodal Diffusion Transformer with a Multimodal Adaptive Fusion module that aligns diverse multimodal inputs for high-fidelity synthesis, and is then distilled into the few-step student AudioX-Turbo via Distribution Matching Distillation adapted to flow matching, complemented by a diffusion-based discriminator for high-quality few-step generation. To support the training of AudioX-Turbo, we construct a large-scale, high-quality dataset, IF-caps-Pro, comprising approximately 9.2M samples curated through a two-stage data collection and annotation pipeline. We benchmark AudioX-Turbo across a wide range of tasks, finding that our model achieves superior performance, especially on text-to-audio and text-to-music generation, while operating at only 4 sampling steps and requiring approximately 25x fewer function evaluations (NFE) than multi-step baselines. These results demonstrate that our method is capable of audio generation under flexible multimodal control, showing efficient and powerful instruction-following capabilities. The code and datasets will be available at https://zeyuet.github.io/AudioX-Turbo/.
Dinghao Zhou, Xingchen Song, Di Wu +3cs.SD cs.AI eess.AS
Continuous audio autoencoders reconstruct waveforms well but often produce latents with weak structure for understanding, while self-supervised audio encoders capture semantics but are not directly decodable. This mismatch complicates a single audio tokenizer that must support both understanding and generation. We adapt continuous autoencoder latents to this setting with two components: a noise-regularized autoencoder bottleneck and a latent-side representation encoder. The bottleneck uses channel normalization and stochastic perturbation instead of KL-based variational training, yielding scale-controlled continuous latents for reconstruction and autoregressive generation. The representation encoder is trained on frozen autoencoder latents with RQ-MTP and frozen-LLM supervision. The resulting tokenizer provides high-dimensional representations for understanding while preserving normalized continuous latents as generation targets
Haitao Li, Tian Tan, Yuguang Yang +2eess.AS cs.AI cs.SD
The rapid advancement of instruction-guided audio generation has highlighted the critical need for robust alignment evaluation. Current automated evaluation methods heavily rely on holistic scoring from general-purpose large language models, which struggle to decouple complex instructions, lack interpretability, and fail to capture fine-grained attribute mismatches. To address this, we introduce a novel dynamic rubric-based evaluation paradigm that adaptively decomposes complex audio captions into a variable number of independent, verifiable binary rubric items. To rigorously benchmark this capability, we propose the AnyAudio-Judge Bench, a comprehensive, bilingual benchmark comprising 7,920 meticulously curated samples across four diverse audio domains (speech, sound, music, and mixed), featuring deliberately constructed hard negatives. Furthermore, we construct a large-scale corpus of 105K samples with explicit Chain-of-Thought (CoT) rationales to train our dedicated evaluator, the AnyAudio-Judge model. By employing a training pipeline that combines Supervised Fine-Tuning (SFT) and Group Relative Policy Optimization (GRPO), our model successfully aligns its reasoning paths with the rubric-based scoring mechanism. Extensive experiments demonstrate that AnyAudio-Judge not only significantly enhances zero-shot alignment detection compared to state-of-the-art baselines, but also provides precise and interpretable reward signals that substantially improve instruction alignment in downstream reinforcement learning for audio generation.
Recent progress in diffusion-based audio generation and restoration has substantially improved performance across heterogeneous conditioning regimes, including text-conditioned audio generation and audio-conditioned super-resolution. However, training audio diffusion models remains computationally expensive, and most existing pipelines still rely on static optimization recipes that treat the relative importance of training signals as fixed throughout learning. In this work, we argue that a major source of inefficiency lies in the evolving balance between semantic acquisition and generation-oriented refinement. Early training places stronger emphasis on acquiring condition-aligned semantic structure and coarse global organization, whereas later training increasingly emphasizes temporal consistency, perceptual fidelity, and fine-detail refinement. To characterize this evolving balance, we introduce a progress-based regime variable derived from the training-time slope of an SSL-space discrepancy, which measures semantic progress during training. Based on this signal, we develop three complementary stage-aware mechanisms: decayed SSL guidance for early semantic bootstrapping, self-adaptive timestep sampling driven by the regime variable, and structure-aware regularization activated from convergent grouped organization in parameter space. We evaluate these mechanisms on text-conditioned audio generation and audio-conditioned super-resolution. Across both settings, the proposed stage-aware strategies improve convergence behavior and yield gains on the primary generation and spectral reconstruction metrics over standard static baselines. These results support the view that efficient audio diffusion training can benefit from treating external guidance, internal organization, and optimization emphasis as stage-dependent components rather than fixed ingredients.