Stability AI Releases Stable Audio 3: A Family of Fast Latent Diffusion Models for Audio Generation and Editing
Quick Answer
Stability AI has launched Stable Audio 3, a series of latent diffusion models for audio generation, featuring small and medium variants with open weights.
Quick Take
Stability AI has launched Stable Audio 3, a series of latent diffusion models for audio generation, featuring small and medium variants with open weights. The medium variant achieves a FAD score of 0.369 on the BBC Sound Effects benchmark, outperforming all evaluated open-weight baselines, and is compatible with consumer GPUs with 8 GB of VRAM.
Key Points
- Stable Audio 3 includes small and medium variants with open weights.
- The small variant runs on MacBook Pro M4 CPU.
- Medium variant generates stereo audio at 44.1 kHz.
- SA3 medium scores FAD 0.369 on BBC Sound Effects benchmark.
- Both models utilize a three-stage training pipeline.
Article Excerpt
From source RSS / original summaryStability 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.
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from MarkTechPost
See more →Meet Flash-KMeans: An IO-Aware, Exact K-Means That Runs Over 200× Faster Than FAISS on GPUs
Flash-KMeans is an open-source, IO-aware k-means implementation that operates over 200× faster than FAISS on NVIDIA H200 GPUs. It achieves 17.9× end-to-end and 33× speedup over cuML by optimizing distance calculations and updating mechanisms without approximating results. This advancement significantly enhances performance for data scientists and machine learning practitioners.