Tag
PianoKontext generates variable-length expressive piano performances from deadpan MIDI scores by aligning audio and MIDI in latent space using Dynamic Time Warping and flow matching with DiT blocks.
An interactive comic that explains harmonics and additive synthesis through visual and auditory demonstrations, created by Sudara and Alec Longstreth.
Google introduces Veo 3.1, an upgraded video generation model with richer audio, improved narrative control, and enhanced realism, alongside significant updates to Flow with new editing capabilities including Insert and Remove features, plus audio support across all existing tools.
OpenAI's Jukebox is a generative model that produces music as raw audio, including vocals and instruments, using a VQ-VAE for compression and hierarchical Sparse Transformer priors to handle long-range musical structure. It represents a significant step beyond symbolic music generation by operating directly in the raw audio domain.