# How to turn a recording into code you can vary with earshot

Repo: [Leonxlnx/earshot](https://github.com/Leonxlnx/earshot) | Difficulty: Advanced | Time: 1 hour | Basis: Seen in the wild

Fit a recording to a small synthesis model and get a Python recipe you can tweak or morph.

**Who it is for:** Developer who has one good sound and wants endless variations or a blend of two sounds

**The problem:** A fixed audio file cannot be resized, retuned or varied, so repeated use sounds identical.

**The outcome:** A recipe module that re-renders the sound with new takes, readable knobs and morphs between two recordings.

## Steps

1. Run `earshot fit click.wav -o made/click_fit.py --report` on your recording.
2. Run the module with `python made/click_fit.py 3 take3.wav` to render a new take.
3. Blend two sounds with `earshot fit --morph a.wav b.wav --amount 0.5 -o made/ab_morph.py`.
4. Explore variations with `earshot fit --forge made/click_fit.py --budget 96 --dir made/click_variations`.

## Prompt to paste into your agent

```text
Use earshot fit to convert <recording.wav> into a recipe module, then render three new takes and describe how they differ. Verify the fit by comparing the side-by-side spectrogram in the report.
```

## Caveat

The fit stores the structure of the sound, not its samples, so very complex or noisy recordings may reproduce only approximately.

## Seen in the wild

- X (Oct 2026): https://x.com/i/web/status/2111362487345971409
- X (Oct 2026): https://x.com/i/web/status/2111229504874246441

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/leonxlnx-earshot/turn-recording-into-editable-sound-recipe/