SANA-Streaming is NVIDIA’s bid at real-time streaming video-to-video editing on consumer GPUs — a use case that’s been a wall for diffusion video models because it demands both temporal consistency frame-to-frame and inference throughput a stream can actually keep up with. ## Hybrid attention, where it counts The architectural move is mixing two attention regimes.… Continue reading

SwanVoice is ByteDance’s bid at expressive long-form zero-shot speech synthesis — a model that can speak in someone’s voice it has never heard before, sustain that voice across minutes of audio, and do it convincingly across both monologue and dialogue. The combination of “long-form” and “expressive” is the hard part most TTS systems quietly skip.… Continue reading

SwanBench-Speech is a benchmark for the part of speech generation that single-utterance demos hide: long form. Most TTS evaluations score short clips on naturalness and prosody. What breaks when you push to minutes of continuous speech — drift, identity loss, expressive monotony — they tend not to measure. ## 1,101 samples across 17 scenarios The… Continue reading

NAVA — Native Audio-Visual Alignment for Generation — comes out of Baidu’s ERNIE research group and stakes a position the field has been edging toward: audio and video should be learned together as one signal, not two separate streams stapled at the seam. ## Native, not stitched Most audio-visual generation pipelines today are bolted together.… Continue reading