TypingMindTypingMindThe best frontend for AI
Midi Synth logo

Midi Synth

Community
maystudios
midi-synth

Synthesize and render MIDI/MusicXML files to audio (WAV/MP3) and generate Strudel live-coding patterns for creative music manipulation. Uses analysis data (tempo, key, chords, dynamics) from audio-to-midi for intelligent ghost-note removal and accurate reproduction. Two workflows: (1) Convert MIDI/MusicXML to Strudel/TidalCycles code with note durations for interactive tweaking in the browser at strudel.cc, (2) Render MIDI/MusicXML to WAV/MP3 with FluidSynth or built-in synthesis, with controls for tempo, transposition, instrument override, and ghost-note cleaning. Trigger when the user wants to: play a MIDI file, render MIDI to audio, synthesize MIDI, convert MIDI to Strudel code, create live-coding patterns from MIDI, change instruments, transpose or tempo-shift, clean ghost notes, or any MIDI playback/synthesis task.

Overview

Publishermaystudios
Repositoryclaude-skills
Skill namemidi-synth
Stars
26
Forks
2
Bundled files
2
LicenseMIT
Links
Skill sourceRepository
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 2 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by maystudios on GitHub. Read the source before you install it.

Installation

Install the Midi Synth AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/maystudios/claude-skills/tree/main/midi-synth
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/maystudios/claude-skills.git /tmp/claude-skills
mkdir -p .claude/skills
cp -r /tmp/claude-skills/midi-synth .claude/skills/midi-synth
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Midi Synth in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Midi Synth on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Midi Synth is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

MIDI Synth

Synthesize MIDI/MusicXML to audio and generate Strudel live-coding patterns. Uses analysis data for ghost-note cleaning, correct tempo, and key-aware filtering.

Scripts

  • scripts/to_strudel.py -- MIDI/MusicXML to Strudel patterns with duration-aware notation
  • scripts/render.py -- MIDI/MusicXML to WAV/MP3 with cleaning and modifications

Both scripts auto-detect *_analysis.json files from audio-to-midi for tempo, key, and dynamics.

Workflow

  1. Identify input: MIDI (.mid) or MusicXML (.musicxml)
  2. Auto-detect or specify the analysis JSON from audio-to-midi
  3. Choose workflow:
    • Creative: to_strudel.py generates Strudel code for strudel.cc
    • Rendering: render.py produces WAV/MP3
    • Both: run both on the same input
  4. Ghost notes are automatically cleaned using velocity, duration, and key filters

Strudel Code Generation

bash
# Basic (auto-detects analysis JSON next to input)
py -3.12 scripts/to_strudel.py "song.mid"

# From MusicXML
py -3.12 scripts/to_strudel.py "song.musicxml"

# Explicit analysis file
py -3.12 scripts/to_strudel.py "song.mid" --analysis "song_analysis.json"

# Stricter ghost-note filtering
py -3.12 scripts/to_strudel.py "song.mid" --min-velocity 60 --min-duration 0.1

# Open in browser
py -3.12 scripts/to_strudel.py "song.mid" --open
FlagDefaultEffect
--analysisauto-detectPath to analysis JSON for tempo/key
--bars4Pattern length in bars
--resolution16Grid: 4/8/16/32
--min-velocity40Remove notes below this velocity (0-127)
--min-duration0.05Remove notes shorter than this (seconds)
--no-key-filteroffDisable key-based ghost note filtering
--tempofrom analysisOverride tempo BPM
--openoffOpen in strudel.cc in browser

Note durations are encoded with @N notation (e.g., c3@4 = held for 4 steps).

Audio Rendering

bash
# Basic (auto-detects analysis, cleans ghost notes)
py -3.12 scripts/render.py "song.mid" --mp3

# From MusicXML
py -3.12 scripts/render.py "song.musicxml" --mp3

# With SoundFont
py -3.12 scripts/render.py "song.mid" --soundfont "GeneralUser_GS.sf2" --mp3

# Aggressive cleaning
py -3.12 scripts/render.py "song.mid" --min-velocity 60 --min-duration 0.1

# Skip cleaning entirely
py -3.12 scripts/render.py "song.mid" --no-clean

# Modifications
py -3.12 scripts/render.py "song.mid" --tempo 2.0 --transpose 3 --instrument 0
FlagDefaultEffect
--analysisauto-detectAnalysis JSON for tempo/key-based cleaning
--min-velocity40Ghost note velocity threshold
--min-duration0.05Ghost note duration threshold (seconds)
--no-cleanoffSkip ghost note removal
--no-key-filteroffDisable key-based filtering
--soundfontauto-detect.sf2 SoundFont path
--tempo1.0Tempo scale factor
--transpose0Semitones up/down
--instrumentoriginalOverride GM program (0-127)
--mp3offAlso produce MP3

Ghost Note Cleaning

Three filter layers (applied in order):

  1. Velocity filter: removes notes below --min-velocity (default: 40)
  2. Duration filter: removes notes shorter than --min-duration (default: 50ms)
  3. Key filter: if analysis provides a key, removes out-of-key notes that also have low velocity (<60)

The key filter only removes notes that are BOTH out-of-key AND below medium velocity, preserving intentional chromatic passages.

Dependencies

Auto-installed: pretty_midi, numpy, soundfile. For MusicXML input: music21 (installed by audio-to-midi skill). Optional: pyfluidsynth + .sf2 SoundFont for high-quality rendering. Runtime: Python 3.12 (py -3.12).

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Midi Synth AI skill do?

Synthesize and render MIDI/MusicXML files to audio (WAV/MP3) and generate Strudel live-coding patterns for creative music manipulation. Uses analysis data (tempo, key, chords, dynamics) from audio-to-midi for intelligent ghost-note removal and accurate reproduction. Two workflows: (1) Convert MIDI/MusicXML to Strudel/TidalCycles code with note durations for interactive tweaking in the browser at strudel.cc, (2) Render MIDI/MusicXML to WAV/MP3 with FluidSynth or built-in synthesis, with controls for tempo, transposition, instrument override, and ghost-note cleaning. Trigger when the user wan...

Why use Midi Synth on TypingMind?

Because you install it once and use it with any model. Midi Synth is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Midi Synth in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/maystudios/claude-skills/tree/main/midi-synth. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Midi Synth?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Midi Synth?

As many as you like. As long as a model supports skills, you can use Midi Synth with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Midi Synth AI skill free?

Yes. It is published on GitHub by maystudios under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

Related AI Skills

View all
openclaw logo

Openclaw Live Updater

openclaw
OrganizationPopular

Maintain the canonical live OpenClaw main checkout, macOS LaunchAgent-managed Gateway, local macOS app, exact-head main CI, and recurring full release validation. Use for fast-forward update…

82.2K
391K
2 files
View
openclaw logo

Openclaw Pr Maintainer

openclaw
OrganizationPopular

Review, triage, repair, or land OpenClaw issues and pull requests with current-source evidence and the native maintainer workflow.

82.2K
391K
5 files
View
openclaw logo

Openclaw Refactor Docs

openclaw
OrganizationPopular

Refactor an existing OpenClaw docs page with source-audited preservation, restructuring, and verification.

82.2K
391K
Instructions
View
openclaw logo

Openclaw Repair Sweep

openclaw
OrganizationPopular

Run scoped OpenClaw issue/PR repair campaigns: coordinate workers, prove root causes, and land or close verified work under the requested authority.

82.2K
391K
1 files
View

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇