MarktechPost·
Stability AI has released Stable Audio 3, a family of latent diffusion models for instrumental music and sound effects generation. The release includes open weights for the small and medium variants. Small runs on a MacBook Pro M4 CPU. Medium fits on consumer GPUs with 8 GB of VRAM. Both generate stereo audio at 44.1 kHz using a three-stage training pipeline: flow matching, distillation warmup, and adversarial post-training. On the BBC Sound Effects benchmark at 5 seconds, SA3 medium scores FAD 0.369 — lower than every open-weight baseline evaluated in the paper. The post Stability AI Releases Stable Audio 3: A Family of Fast Latent Diffusion Models for Audio Generation and Editing appeared first on MarkTechPost.
Read full articleMusic v2 brings genre-shifting and section-by-section composition to ElevenLabs. Stable Audio 3.0 ships open weights and six-minute tracks. Is either good enough to dethrone the category leader?
Booz Allen and Future Tech leaders share how using hybrid design, edge AI and GPUs can accelerate secure federal AI deployment.
Stable Audio 3.0's extended capabilities could revolutionize on-chain music economics, enhancing royalty management and NFT music marketplaces. The post Stability AI releases Stable Audio 3.0 with six-minute song generation capabilities appeared first on Crypto Briefing.
Stability Audio 3.0 small model can run on-device and generate two-minute long tracks
Zyphra's latest release shows that an autoregressive MoE model can be converted into a discrete diffusion model with no systematic loss in evaluation performance. ZAYA1-8B-Diffusion-Preview achieves up to 7.7x inference speedup over autoregression by shifting decoding from memory-bandwidth bound to compute-bound — a key advantage as modern GPUs continue scaling FLOPs faster than memory bandwidth. The post Zyphra Releases ZAYA1-8B-Diffusion-Preview: The First MoE Diffusion Model Converted From an Autoregressive LLM With Up to 7.7x Speedup appeared first on MarkTechPost.
The idea of asking homeowners to host boxes full of GPUs is a symptom of the woeful dearth of data center space needed for AI computing.
Silicon photonics is emerging as a way move massive amounts of data among GPUs and CPUs in HPC systems, but what if you could compute purely with light and photonics? […] The post Lumai’s Photonic Chip Harnesses Light for Big AI Compute Speedup appeared first on AIwire.
This Spring Astronomy Day, here’s a look at how AI and GPUs are helping astronomers work through unprecedented volumes of cosmic data.
