Auto-voicing chord symbols is a notoriously difficult theory challenge. The Voicify keyboard utilizes the THIRI API’s /v2/voicing endpoint to bypass hardcoded rules.

By requesting voicings with specific styles (such as “rootless” or “drop-2”), the system automatically distributes the midi notes across the piano keys in a human-like fashion.

Sample Voicing API Request:

{
  "chord": "Dm9",
  "style": "rootless",
  "octave": 4,
  "voices": 4
}

🤖 File an Issue for an Autonomous Coding Agent

This project requires setting up an external application or workflow environment. If you want an autonomous coding agent (like Claude Code) to implement it in your repository:

Click here to open a pre-filled GitHub Issue on the repository
Submit the issue to trigger your repository’s autonomous builder agent.

Alternatively, you can copy the raw agent prompt instruction below:

Task Context: Build a code project utilizing the THIRI Model Context Protocol (MCP) server. Prompt Instruction: Write a Node.js utility that listens to chord symbols from standard input, queries the THIRI MCP generate_voicing tool with configurable style parameters (e.g. rootless, open-gospel, close-clusters), and outputs a formatted MIDI file containing the resolved MIDI voicing pitches voiced in correct keyboard registers.

Get Started: Voicify: Auto-Generating Professional Piano Voicings

Sample Voicing API Request:

🤖 File an Issue for an Autonomous Coding Agent

Trends