What is audio-to-midi?

An audio transcription tool that turns recorded sound into MIDI files and MusicXML, formats used by music software to represent notes and scores. It can analyse tempo, key, chords, dynamics, and instruments.

Use it to transcribe mixed or polyphonic music, piano or keyboard recordings, and create MIDI or MusicXML files for editing, notation, or further analysis.

It removes the need to enter music notes by hand from an MP3, WAV, FLAC, or similar recording. Optional stem separation can split vocals, drums, bass, and other sounds before transcription.

audio-to-midi — Skill for Claude Code and Codex by maystudios

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add maystudios/claude-skills --skill audio-to-midi

Clone the repo

git clone --depth 1 https://github.com/maystudios/claude-skills

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/maystudios/claude-skills/audio-to-midi/github.svg)](https://agentmods.dev/skills/maystudios/claude-skills/audio-to-midi)

Your own site

<a href="https://agentmods.dev/skills/maystudios/claude-skills/audio-to-midi"><img src="https://agentmods.dev/badge/skills/maystudios/claude-skills/audio-to-midi/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/maystudios/claude-skills/audio-to-midi"><img src="https://agentmods.dev/badge/skills/maystudios/claude-skills/audio-to-midi.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 186 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,252 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00186	$0.01252
Opus 5	$0.00093	$0.00626
Sonnet 5	$0.00037	$0.00250
Haiku 4.5	$0.00019	$0.00125

Measured 11d ago against content hash f3ceb2c7338c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

audio-to-midi scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/transcribe.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

audio-to-midi/SKILL.md · 115 lines

How it starts

The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Audio-to-MIDI Transcription

Convert audio files to MIDI and MusicXML with full music analysis (tempo, key, chords, dynamics, instruments).

Tool

Script: scripts/transcribe.py -- wraps Basic Pitch, Demucs, librosa, and music21. Auto-installs dependencies.

Workflow

Identify the input audio file (MP3, WAV, FLAC, OGG, M4A)
Determine options:
- Stems? Add --stems to separate vocals/drums/bass/other with Demucs first
- Output dir? Use -o path or default to input file's directory
- Skip analysis? Add --no-analysis if only MIDI/MusicXML needed
- Skip MusicXML? Add --no-musicxml if only MIDI needed
Run the transcription script
Report output files and analysis summary to user

Engines

Engine	Flag	Best for	Accuracy
Basic Pitch	`--engine basic-pitch` (default)	Mixed/polyphonic music	Good
Piano Model	`--engine piano`	Piano/keyboard music	96.7% F1

For piano or keyboard music, always use --engine piano — it captures sustain/pedal, has far fewer ghost notes, and produces much more accurate MIDI.

Usage

# Piano music (recommended for piano/keyboard)
py -3.12 scripts/transcribe.py "piano.mp3" --engine piano

# General music (default engine: Basic Pitch)
py -3.12 scripts/transcribe.py "song.mp3"

# With stem separation (Demucs): each stem gets its own MIDI + MusicXML
py -3.12 scripts/transcribe.py "song.wav" --stems

# Custom output directory
py -3.12 scripts/transcribe.py "song.mp3" -o ./output --engine piano

# Tuning Basic Pitch sensitivity
py -3.12 scripts/transcribe.py "song.mp3" --onset-threshold 0.6 --frame-threshold 0.4

# MIDI only (skip MusicXML)
py -3.12 scripts/transcribe.py "song.mp3" --no-musicxml

# MIDI + MusicXML without analysis
py -3.12 scripts/transcribe.py "song.mp3" --no-analysis

Output Files

For input song.mp3:

song.mid -- MIDI file (for DAWs, notation software)
song.musicxml -- MusicXML (for MuseScore, Finale, Sibelius, Dorico)
song_analysis.json -- Full analysis (tempo, key, chords, dynamics, spectral)

Read the full file on GitHub · 115 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

scripts/transcribe.py 13 KB runs code

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

11d ago First seen · 115 lines · 186 tokens per session scan A f3ceb2c7338c

Subscribe to this mod's changes

audio-to-midi is a skill published in the GitHub repository maystudios/claude-skills (22 stars, last pushed 27d ago), licensed MIT. It adds 186 tokens to every session and 1,252 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Claude Code Creative and media agent-skills ai-coding claude-skills llama-cpp ue5

presentation-chef

Convert any content into a stunning Apple Keynote-style HTML presentation. Takes markdown, text descriptions, or structured data and generates a single self-contained .html file with cinematic animations, glassmorphism, and premium design. Inspired by ChronicleHQ.

sacredvoid/skillkit · 52 tokens

creative-code-lab

Use when user asks to create generative art, creative coding sketches, visual experiments, particle systems, shader effects, procedural graphics, interactive canvases, or any code-as-art project. Use when building animated backgrounds, flow fields, fractals, L-systems, noise-based visuals, text effects, fluid…

sacredvoid/skillkit · 113 tokens

icons8

Fetch icons, illustrations, and photos from Icons8. Search 1.5M+ icons across 116 styles, vector illustrations, and 500K+ stock photos. Supports API (with key) and free CDN fallback (no key needed).

sacredvoid/skillkit · 53 tokens

logo-generator

Generate custom logos with adaptive brainstorming and full brand kit export. Scans project context (README, package.json, CSS, existing assets) to inform design. Outputs favicons (16-512 + ICO), social images (OG, Twitter), dark/light/mono SVG variants, and an HTML preview.

sacredvoid/skillkit · 63 tokens

local-image-gen

Generate custom images locally using Stable Diffusion. Auto-detects your hardware (Apple Silicon, NVIDIA, AMD, CPU) and picks the best model and settings. Supports single and batch modes. Cross-platform: macOS, Linux, Windows.