Every premium and members-only resource for $9.99/month, as a no-commitment subscription. See the plans

PalateKit

Sign in
Menu

Request a resource

Describe the resource you are missing in one sentence. We will email you when it is published.

0 / 280

A page, a video or an image online.

Unlock PalateKit

Unlock everything

Plan

Paying means accepting our terms of sale.

Secure payment by Stripe. Receipts and invoices sent by email.

Welcome back

Sign in to install, download or save this resource. A free account is enough for free resources.

Automatically duck music under a voice track v1.0.0

Use this resource to mix a music bed under a voice track, without manual volume automation

New

  • 442 downloads
  • 225 likes
  • 206 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install music-bed-voice-ducking

With no option, the skill goes to ~/.agents/skills/; add --agent claude-code (or codex, cursor…) to target an agent.

First time: connect the CLI with

npx --yes palatekit@latest login

The agent sends the music and the voice track to Sonilo, which lowers the music during spoken passages and raises it in the pauses. If the voice comes from a video, its audio track is used and the mix is muxed back into a new video. You get the final mix.

Mostly picked by

Updated November 2, 2026

Card for the “Automatically duck music under a voice track” skill

Details

Works in
Install guides
Generates with
Your agent's model
Licence
MIT

Similar resources

View all

What you get

  • SKILL.md : mixing tool and parameters for voice and music
  • SKILL.md : workflow tips for a clean mix

Good fit for

  • You are mixing music under a narration
  • You have a generated track to place under dialogue

Not for

    Tags

    • ducking
    • mixing
    • music
    • voice
    • audio

    About

    You say

    “Mix this music under my narration, lowering it while I speak.”

    Card for the “Automatically duck music under a voice track” skill

    Skill published by sonilo-ai under the MIT license, delivered in its original version.

    Show more

    How to use it

    1. Install the skill in your agent's skills folder
    2. Ask your agent to mix a music bed under a voice track, without manual volume automation
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1.1 KB
    • NOTICE-PALATEKIT.md0.4 KB
    • SKILL.md7 KB

    Origin and licence

    Listed unmodified

    Author
    sonilo-ai
    Source
    github.com/sonilo-ai/skills/tree/64c79d0f227a2f016a655292da8cc8382735396e/audio-ducking
    Licence
    MIT

    Notice

    « audio-ducking » (sonilo-ai, MIT) livré dans sa version d'origine : fiche en français et en anglais par PalateKit.

    User reviews

    –

    No ratings yet

    Loading reviews…

    Delete your review?

    Your rating and comment will be removed from the page.