Clean Codec Artifacts from AI-Generated Music

Traditional audio enhancers (EQ + compression + denoise) assume the input is "clean signal plus additive noise". AI-generated music contains structural codec artifacts that violate this assumption — generic enhancers can amplify them. This tool uses a different approach: a model trained on codec-artifact restoration specifically.

Apollo is a neural network published at ICASSP 2025 (Li et al., "Apollo: Band-sequence Modeling for High-Quality Audio Restoration"). It was trained to restore MP3-compressed music to lossless quality. The same architecture works well on neural codec artifacts from SUNO and Udio.

Apollo is trained on music. For speech cleanup (interviews, podcasts), use our Audio Enhancer or Voice Enhancer tools — they target speech-specific noise patterns.

A 3-minute song takes about 30 seconds to 4 minutes depending on your device. WebGPU-capable browsers (recent Chrome / Edge) are 3-5× faster than CPU-only.

Anything that came out of a neural audio codec at low bitrate — SUNO free tier (≤ 128 kbps), Udio downloads, Riffusion exports, also old MP3s ripped at 96–128 kbps. Lossless inputs (FLAC, WAV from a DAW) gain little. Heavily damaged material (clipping, dropouts) is outside the model's training distribution — try the Audio Restoration tool first.

No. The restoration runs in your browser — your audio file is not sent to us. We log only anonymous performance events (model load time, inference duration) to spot bugs and improve speed; see the Privacy Policy.

Yes. The artifact profile from neural audio codecs is similar across these tools — Apollo handles all of them. Best results on the same family of damage it was trained on (MP3-style codec loss).

WAV (uncompressed, lossless, largest file), FLAC (lossless, ~50% smaller than WAV) and MP3 (lossy, smallest). WAV preserves the maximum quality of the restoration.