Show HN: Musslop – turn any track into adaptive game-style music loops

Developer Siziff released musslop, an open-source tool that uses AI to turn any MP3 into adaptive, game-style music loops, with a flagship use case for tabletop RPG sessions. Musslop runs locally via a Python setup script and serves at http://localhost:8801, using SongFormer (2025) and All-In-One (2023) neural engines for structure analysis, Beat This! for beat and downbeat tracking, and Demucs for splitting tracks into drums, bass, vocals, and backing layers. First AI analysis takes about 1 minute on GPU or a few minutes on CPU, with results cached for instant reopening, and the tool works fully offline after setup.

Loop any section forever · hit «Next» · the music evolves — seamlessly, on the beat In games, music reacts : stay in the tavern and its theme loops forever; descend into the dungeon and the score darkens with you. musslop does this with any mp3. Drop a track → AI finds the musical structure → every section becomes a perfect loop → you drive the music live, like a game audio engine — no editing skills required. | Feature | What it does | |---|---| | AI structure analysis | two neural engines find sections and name them Intro, Verse, Chorus, Solo : SongFormer https://github.com/ASLP-lab/SongFormer 2025, faster, best on pop/rock/electronic and All-In-One https://github.com/mir-aidj/all-in-one 2023, steadier on orchestral ; beats/downbeats via Beat This https://github.com/CPJKU/beat this . Fast heuristic fallback ~2 s works everywhere | | Seamless loops | sample-accurate Web Audio scheduling, bar-snapped boundaries, per-section loop-quality score ⟳% , equal-power crossfades | | Intensity layers | Demucs splits the track into drums / bass / vocals / backing — toggle and mix layers live: calm exploration → full combat, same track | | Pro transitions | post-exit tails ring out over the next section, bass-swap keeps exactly one bassline at any moment, one-shot stingers cymbal / boom / riser punctuate scene changes | | Knows what not to loop | build-ups are detected by their crescendo shape and play once, as dramatic bridges | | Full editor | drag boundaries with bar snapping, split/merge, loop-start markers, Ctrl+Z, zoom + scrollbar, everything auto-saved | The flagship use case is tabletop RPG : turn any track into a location theme . The party lingers in the tavern — the tavern section loops. They open the dungeon door — one keypress, and the music descends with them, on the beat, mid-session. There is even a Tavern UI theme wood, parchment & gold switchable in the header. Also great for: game dev prototyping audition adaptive behaviour before wiring FMOD/Wwise, export loop WAVs , streaming, practice looping, focus music. Linux / macOS: git clone https://github.com/Siziff/musslop.git && cd musslop ./setup.sh creates .venv, installs everything incl. a bundled ffmpeg ./run.sh → http://localhost:8801 Windows needs Python 3.10+ https://python.org with "Add to PATH" checked : git clone https://github.com/Siziff/musslop.git cd musslop setup.bat run.bat → http://localhost:8801 ffmpeg is downloaded automatically with the dependencies — no manual install needed. Optional AI engines each is one command, both auto-detected by run.sh : Linux / macOS: ./setup-ai-songformer.sh SongFormer 2025 + Beat This — newer, faster, best on pop/rock/electronic; plain pip, no compilers ./setup-ai-allin1.sh All-In-One 2023 + Demucs — steadier on orchestral, also powers the stem "layers" feature Windows: setup-ai-songformer.bat needs git in PATH; ~15 min, ~4 GB The All-In-One engine is not supported natively on Windows its NATTEN dependency needs a source build ; use WSL2 with the Linux script if you need it. SongFormer covers structure analysis fully, and the stem "layers" feature also works through it on Windows. Works fully offline after setup. First AI analysis of a track: ~1 min on GPU, a few minutes on CPU; results are cached — reopening is instant. 1. Beat & downbeat tracking — onset envelope + dynamic programming Ellis 2007 2. Structure — neural All-In-One, WASPAA 2023 or Foote novelty on beat-synced chroma+MFCC+RMS self-similarity 3. Loop-aware refinement — boundaries move along downbeats maximizing loop closure quality head/tail spectral similarity , phrase lengths 4/8 bars and transition audibility 4. Build-up detection — normalized RMS slope + trend R² + spectral-centroid rise 5. Playback — every loop pass is an independent AudioBufferSourceNode ; transitions land on loop/phrase boundaries with micro-fades, tails and bass-swap Built on the shoulders of: SongFormer https://github.com/ASLP-lab/SongFormer ASLP-lab, CC-BY-4.0 · All-In-One https://github.com/mir-aidj/all-in-one Kim & Nam, MIT · Beat This https://github.com/CPJKU/beat this CPJKU, MIT · Demucs https://github.com/facebookresearch/demucs · librosa https://librosa.org — plus classic MIR: Ellis 2007 beat tracking , Foote 2000 novelty segmentation . | Endpoint | Purpose | |---|---| | POST /api/upload · POST /api/import url | file upload / yt-dlp import | | GET /api/analyze/{id}?engine=fast\|deep | structure analysis | | POST /api/stems/{id} · GET /api/stems/{id}/{stem} | Demucs 4-stem split | | POST /api/export/{id} | zip of full-quality loop WAVs | | GET/POST /api/markup/{id} | segment markup persistence | | GET /api/tracks · POST /api/favorite/{id} | history & library | 1. curl http://localhost:8801/api/health → expect {"status":"ok", ...} 2. Blank page → hard-refresh Ctrl+F5 , check browser console F12 3. Port busy → ./run.sh frees it; manually: lsof -ti tcp:8801 | xargs kill 4. No sound → click the ♪? self-test in the volume box bottom-right 5. Server errors → server.log