Stable Audio Open

The 'Stable Audio Open' dataset/benchmark contains audio samples used to evaluate the effectiveness of generative audio models in achieving controllable outputs, such as intensity, pitch, and beats.

Papers using Stable Audio Open (4)

Fast Text-to-Audio Generation with Adversarial Post-Training2025 · 13 citesLow-Resource Guidance for Controllable Latent Audio Diffusion2026Post-Training Quantization for Audio Diffusion Transformers2025SmoothCache: A Universal Inference Acceleration Technique for Diffusion Transformers2024