# AI use cases for Resonant (calesthio/Resonant)

Repo: [calesthio/Resonant](https://github.com/calesthio/Resonant) | Use cases: 5 | Page: https://dedupedai.com/use-cases/calesthio-resonant/

Resonant is a free, open-source AI music studio for Windows that generates, arranges, mixes, and exports songs locally, and can be operated by AI assistants through an MCP server.

This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL.

- Build a full song by asking an AI assistant: https://dedupedai.com/use-cases/calesthio-resonant/build-full-song-from-ai-assistant/
- Generate a vocal or instrumental song locally: https://dedupedai.com/use-cases/calesthio-resonant/generate-vocal-song-with-ace-step/
- Convert a vocal stem into your own singing voice: https://dedupedai.com/use-cases/calesthio-resonant/convert-own-vocal-with-seed-vc/
- Write, arrange, mix, and export a song in Resonant: https://dedupedai.com/use-cases/calesthio-resonant/write-arrange-mix-export-song-in-studio/
- Run Resonant from source and build its MCP server: https://dedupedai.com/use-cases/calesthio-resonant/run-resonant-from-source/

## How to build a full song by asking an AI assistant with Resonant

Repo: [calesthio/Resonant](https://github.com/calesthio/Resonant) | Difficulty: Intermediate | Time: 60 minutes | Basis: From the README

Connect Codex or Claude to Resonant over MCP and request a finished WAV from one plain-language prompt.

**Who it is for:** A songwriter or producer who wants a complete draft song fast and already uses Codex or Claude Code.

**The problem:** Programming every lyric, section, instrument, and mix setting by hand takes hours before a song can be judged.

**The outcome:** A complete arranged song exported as a stereo WAV in a chosen music workspace, with the assistant having operated Resonant's saved project tools.

### Steps

1. Download the Windows installer from the Releases page and install Resonant.
2. In Resonant, open Quick Start, choose Connect Codex, Claude, or another AI assistant, and select the folder that will hold your .resonant projects.
3. Paste the generated configuration into your client, for example .mcp.json for Claude Code, then restart the assistant.
4. Run /mcp in the assistant and confirm that resonant is connected, then save or open a .resonant project.
5. Send your song request and ask the assistant to call get_capabilities before it starts.

### Prompt to paste into your agent

```text
Using the Resonant repo at https://github.com/calesthio/Resonant, connect to its local MCP server with the workspace folder <music-folder>. Ask Resonant to write an original song, arrange it, leave mix headroom, analyze it, and export a WAV. Expected output: the exported WAV path inside <music-folder>; verify by calling get_capabilities first and confirming the file exists.
```

### Caveat

The downloadable Windows builds are unsigned, so SmartScreen may warn, and agent writes are limited to the workspace folder you choose.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/calesthio-resonant/build-full-song-from-ai-assistant/

## How to generate a vocal or instrumental song locally with Resonant

Repo: [calesthio/Resonant](https://github.com/calesthio/Resonant) | Difficulty: Intermediate | Time: 90 minutes | Basis: From the README

Use the AI SONG control to create a complete original song on your own machine with ACE-Step 1.5.

**Who it is for:** A musician who wants a fresh song idea from a written direction and lyrics without uploading anything to the cloud.

**The problem:** Cloud generators charge credits or subscriptions and upload your prompts and output.

**The outcome:** A generated song on Resonant's Audio track, ready to arrange and mix in the workstation.

### Steps

1. Install Resonant and open the header control labeled AI SONG.
2. Install and start the optional ACE-Step 1.5 generator from inside Resonant.
3. Enter a musical direction, lyrics, tempo, duration, and choose vocal or instrumental.
4. Generate the song and wait while the initial model download completes; later generation runs locally.
5. Drag the generated performance into the arrangement timeline and mix it.

### Prompt to paste into your agent

```text
Using the Resonant repo at https://github.com/calesthio/Resonant, generate a vocal song with ACE-Step 1.5 from the direction <style-prompt> and lyrics in <lyrics-file>. Expected output: a generated performance on the Audio track; verify that the model download finished and the clip plays before arranging it.
```

### Caveat

The recommended Windows laptop profile needs a large initial model download and an NVIDIA GPU with roughly 6 to 8 GB VRAM is recommended.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/calesthio-resonant/generate-vocal-song-with-ace-step/

## How to convert a vocal stem into your own singing voice with Resonant

Repo: [calesthio/Resonant](https://github.com/calesthio/Resonant) | Difficulty: Advanced | Time: 120 minutes | Basis: From the README

Use MY VOICE and Seed-VC to turn an isolated vocal into a new WAV in your consented voice.

**Who it is for:** A singer or producer with a separated vocal stem who wants a performance sung in their own voice.

**The problem:** Recording every take again is slow, and a full mix cannot be converted cleanly.

**The outcome:** A converted WAV on the Audio track that keeps the melody, timing, and phrasing of the source vocal.

### Steps

1. Install Resonant and open the header control labeled MY VOICE.
2. Install and start the optional Seed-VC provider from inside Resonant.
3. Choose an isolated source vocal and a clean 1 to 30 second reference recording you own.
4. Confirm that you own the voice or have explicit permission to use it, then start the conversion.
5. Check the converted WAV on the Audio track before arranging and mixing it.

### Prompt to paste into your agent

```text
Using the Resonant repo at https://github.com/calesthio/Resonant, start a Seed-VC conversion of <source-vocal.wav> using the consented reference <my-voice.wav>, with both files inside the music workspace. Expected output: a converted WAV in the workspace; verify that voiceRightsConfirmed is true and that the conversion status reports complete before collecting the result.
```

### Caveat

Seed-VC needs an NVIDIA CUDA GPU, uses about 5 GB after installer caches are cleaned, and is GPL-3.0 licensed and installed separately from Resonant.

Risk, voice cloning: Only convert a voice you own or have explicit permission to use, because Resonant requires that confirmation and records source and reference hashes.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/calesthio-resonant/convert-own-vocal-with-seed-vc/

## How to write, arrange, mix, and export a song in Resonant with Resonant

Repo: [calesthio/Resonant](https://github.com/calesthio/Resonant) | Difficulty: Intermediate | Time: 60 minutes | Basis: From the README

Draft lyrics in Songwriter Studio, build a song on the timeline, mix it, and export a stereo WAV.

**Who it is for:** An independent songwriter who wants full control over structure, sound, and final mix without a cloud service.

**The problem:** Songs often stall between writing lyrics and getting a finished, exportable mix.

**The outcome:** A saved project and a deterministic stereo WAV export of a complete arranged song.

### Steps

1. Install Resonant from the Windows installer, then launch it and start with the built-in groove or a blank project.
2. Develop the hook, sections, and lyrics in Songwriter Studio and review the live coaching signals.
3. Build clips with the instrument library, then launch clips and scenes in the clip launcher.
4. Arrange the ideas on the arrangement timeline, then set levels, pan, and master limiting in the mixer.
5. Save the project and export the stereo WAV.

### Prompt to paste into your agent

```text
Using the Resonant repo at https://github.com/calesthio/Resonant, help me write lyrics for a song about <theme> in Songwriter Studio and outline its sections. Expected output: a lyric draft with a section list; verify that the chorus repeats intentionally and the section count fits the target length.
```

### Caveat

The README describes Resonant as a Windows studio, so macOS and Linux users are not covered by these steps.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/calesthio-resonant/write-arrange-mix-export-song-in-studio/

## How to run Resonant from source and build its MCP server with Resonant

Repo: [calesthio/Resonant](https://github.com/calesthio/Resonant) | Difficulty: Advanced | Time: 45 minutes | Basis: From the README

Clone the public repo, install locked dependencies, and build the MCP runtime for inspection or development.

**Who it is for:** A developer who wants to audit the code, change it, or run the MCP server from a checkout instead of the installer.

**The problem:** Unsigned prebuilt executables are hard to verify, so some users want to build from public source.

**The outcome:** A locally built Resonant running from source with the MCP runtime compiled.

### Steps

1. Install Git for Windows and Node.js 22 or newer.
2. Clone the repository with git clone https://github.com/calesthio/Resonant.git and change into the Resonant folder. (inferred, check the README)
3. Run npm ci to install the locked dependencies.
4. Run npm run build:mcp to build the MCP server.
5. Launch the app as described in the source install section and confirm the MCP server connects to your client.

### Prompt to paste into your agent

```text
Using the Resonant repo at https://github.com/calesthio/Resonant, clone it into <target-folder>, run npm ci and npm run build:mcp, and report any errors. Expected output: a successful build with no failures; verify by checking that the MCP build step exits with success before connecting a client.
```

### Caveat

Source builds need Node.js 22 or newer, and the README says the repository already includes starter Codex and Claude configurations.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/calesthio-resonant/run-resonant-from-source/