Music Listener
From its catalog listing
Listen to an MP3/FLAC/WAV by reconstructing every instrumental track, the vocal melody, pitch contour and time-aligned lyrics into a multi-track MIDI, MusicXML score and a compact structural JSON. Runs a heavy audio/ML stack (Demucs htdemucs_6s 6-stem separation, Spotify Basic Pitch polyphonic transcription, librosa pyin f0, faster-whisper lyric alignment) inside its own isolated Python 3.11 venv so Hermes' core runtime is never touched. The listen_to_music tool accepts an audio path and returns artifact paths (full_score.mid, full_score.musicxml, score_summary.json) plus tempo, key, per-track note counts, 8-bar section descriptors and synced lyric words — a compact structural summary so the agent reasons over the song without loading thousands of raw MIDI events. A /listen slash command and the music-listener:music-listener skill (pretty_midi/music21 recipes for bar queries, motifs, transposition and re-harmonization) round out the working surface. The worker prints progress to stderr and only compact JSON to stdout. Security: no shell=True (argv-list subprocesses), sanitized output paths, no credential reads, no network ports, a 60-minute worker cap; its only outbound traffic is official Demucs/faster-whisper model-weight downloads. Proven end-to-end on a real 2:46 commercial track (Imael Angel - "Bad Times"): 7 named MIDI tracks, valid MusicXML, 100 time-aligned lyric words. See https://github.com/JPeetz/music-listener#readme.
Good to know before installing
after install you run the plugin's install.sh, which builds a Python 3.11 venv inside the plugin folder and downloads about 1-2 GB of packages (torch, Demucs, faster-whisper); the first transcription downloads Demucs and faster-whisper model weights from their upstream hosts; listen_to_music reads whatever audio path the agent passes and writes stems and scores under transcriptions/ in the agent's working directory (or the configured output_dir), running a CPU/GPU-heavy worker for up to 60 minutes per call.
From its catalog listing.
How to install
- Install it. Hermes asks for any API keys it needs, then asks whether to turn it on.
hermes plugins install music-listener - Said no? Turn it on later:
hermes plugins enable music-listener - Restart Hermes so it loads the plugin.
Some plugins also need a sign-in or settings: see Full setup & settings. Memory plugins ask whether to become your memory provider instead. Steps follow the official plugins guide (opens in a new tab).
- Category
- Memory & notes · Images, video, music & 3D
- Maintained by
- JPeetz (Community)
- Needs
- No API keys declared
- Adds tools
listen_to_music- Works on
- macos, linux
- Needs Hermes
- 0.21.5 or newer
- Version
- 0.1.0
- In the catalog
- 2026-11-17
Known issues (from its catalog listing)
- On Intel-mac CPU-only hosts, torch must stay at 2.2.2 and torchcrepe's full.pth CPU inference hangs; the worker uses librosa pyin behind a 30s watchdog as its reliable f0 path. Memory-ordered stages keep whisper from OOMing 16 GB hosts.
Using the Hermes desktop app? See where plugins live

Full setup & settings ↗Source code ↗
More in memory & notes
New Hermes Agent updates every day on X. Follow @HermesWatcher