Ever struggled with cleaning up home-recorded music? Issues like weird echoes, distortion, uneven sound, or mastering to bring your music up to production-level quality can be a huge pain to fix — usually needing several different tools and lots of tweaking.

We just released SonicMaster, a model that aims to simplify this process by handling all those common problems in one place. The coolest part? You can control it with simple text instructions ('Make the audio smoother and less distorted.'') or let it automatically restore your audio.

• Listen to examples
• Read paper
• GitHub
• Dataset

It’s a step toward making professional-quality music restoration and mastering more accessible to creators without a studio or specialized gear.

Highlights:

• Unified Restoration: all-in-one model to simultaneously handle reverb, clipping, EQ, dynamics, and stereo imbalances.
• Text-based control: use natural-language instructions (e.g. “reduce reverb”) for fine-grained audio enhancement.
• High-quality output: objective metrics (FAD, SSIM, etc.) and listening tests show significant quality gains.
• SonicMaster dataset: We release a large-scale dataset of 25k (208 hrs) paired clean and degraded music segments with natural-language prompts for training and evaluation.

Thanks to the main authors Jan Melechovsky, Abhinaba Roy and Ambuj Mehrish from the AMAAI Lab at Singapore University of Technology and Design (SUTD).

Would love to hear your thoughts or experiences with audio restoration and your music production / mastering needs. We'd love to bring SonicMaster to the next level.