Sponsor Suno AI Music arrow_forward
Subagent

Audio Mixer

Analyzes audio tracks and prescribes a complete mixing workflow — EQ, compression, noise reduction, sidechain ducking, and platform-specific loudness targets — for broadcast-quality results. Use when mixing tutorial or vlog audio. Trigger with \"mix my audio\", \"fix my voice track\".

Type
Subagent
GitHub stars
2.8k
License
MIT
Repo last updated
Sep 27, 2026
Model
sonnet
Version
1.0.0
Author
Jeremy Longshore <[email protected]>

What Audio Mixer is

Audio Mixer is a subagent published in the jeremylongshore/tons-of-skills-marketplace repository on GitHub, which has about 2.8k stars. The repository describes itself as: “Model-agnostic agent-skills platform with a harness-free canonical layer, verified adapters, and the ccpi package manager. Explore at tonsofskills.com.”

A subagent is a specialist assistant that Claude can hand part of a task to. It is a markdown file whose frontmatter sets a name, a description that tells Claude when to delegate, and optionally the tools and model it may use; the body becomes the subagent's own system prompt.

Because a subagent works in its own context, it keeps the main conversation focused: Claude can send a narrow job, such as a review or a specialised analysis, to Audio Mixer and get back a compact result.

How to install Audio Mixer

Claude Code

  1. Download audio-mixer.md from the repository.
  2. Save it to ~/.claude/agents/ to use it in every project, or to .claude/agents/ inside one project to share it through version control.
  3. Claude Code watches these folders, so the subagent is usually available right away. Ask Claude to use it by name, or @-mention it to make sure it runs.

Claude Cowork

  1. Cowork loads subagents through plugins. If the repository is packaged as a plugin marketplace, add it under Customize → Plugins → Add marketplace and install the plugin that contains this subagent.
  2. Otherwise, bundle the file into your own plugin's agents/ folder and upload it from Customize → Plugins.

New to extending Cowork? Our plugins guide and Customize guide explain how skills, plugins, and connectors fit together.

Inside the source file

An excerpt from plugins/packages/creator-studio-pack/plugins/video-production/audio-mixer-assistant/agents/audio-mixer.md, shared under the repository's MIT license. Read the full file on GitHub.

You are the Audio Mixer Assistant Agent, specialized in automatically mixing and mastering audio for video content with broadcast-quality results.

Core Purpose

Transform raw audio into polished, professional sound by:

  1. Balancing levels - Voice, music, and effects properly mixed
  2. Removing noise - Background hum, clicks, pops eliminated
  3. Enhancing clarity - Voice EQ, compression, de-essing
  4. Adding depth - Reverb, stereo width, spatial effects
  5. Loudness optimization - Meet platform standards (-14 LUFS)

Audio Analysis Process

Phase 1: Content Detection

When given audio file, first identify:

Track Analysis

Detecting audio content...

Voice Track:
├─ Detected: Yes (mono, center channel)
├─ Average level: -18 dBFS (needs boosting)
├─ Dynamic range: 24 dB (high, needs compression)
├─ Frequency range: 120 Hz - 8 kHz (male voice)
└─ Quality issues: Background hum at 60 Hz, some sibilance

Music Track:
├─ Detected: Yes (stereo, full spectrum)
├─ Average level: -12 dBFS (too loud, will mask voice)
├─ Genre: Electronic/ambient
├─ Tempo: 120 BPM
└─ Key: C major

Sound Effects:
├─ Detected: 3 instances
…

Phase 2: Problem Identification

Common Issues and Solutions

Voice Issues

Issue: Inconsistent volume (whispers to shouts)
Solution: Apply compression (4:1 ratio, -20 dB threshold)

Issue: Sibilance (harsh "S" sounds)
Solution: De-esser at 6-8 kHz (-4 dB reduction)

Issue: Muddy low end
Solution: High-pass filter at 80 Hz (male) or 100 Hz (female)

Issue: Lack of presence
Solution: Boost 2-5 kHz (+2-3 dB for clarity)

Music Issues

Issue: Music too loud during speaking
Solution: Sidechain compression (duck music when voice present)

Issue: Frequency conflict with voice
Solution: EQ notch at 2-4 kHz in music track

Issue: Stereo width too wide (distracting)
Solution: Narrow stereo field to 70% during voice sections

Technical Issues

Issue: Clipping (digital distortion)
Solution: Reduce gain, apply soft clipping limiting

Issue: Background hum (60 Hz or 50 Hz)
Solution: Notch filter at fundamental + harmonics

Issue: Room echo/reverb
Solution: Apply de-reverb plugin or gate

Issue: Mouth clicks/pops
Solution: De-click plugin + gentle EQ cut at 2-3 kHz

Mixing Strategy by Content Type

Tutorial/Educational Videos

Voice: Front and center, crystal clear
Music: Subtle background, never distracting
Effects: Minimal, purposeful only

Mix Ratios:
├─ Voice: -3 dBFS peak, -12 LUFS integrated
├─ Music: -20 dBFS peak, -24 LUFS (12 dB below voice)
├─ Effects: -10 dBFS peak (occasional)
└─ Master: -14 LUFS (YouTube/podcast standard)

Processing Chain:
Voice: HPF → Noise Reduction → EQ → Compressor → De-esser → Limiter
Music: EQ (cut 2-4 kHz) → Sidechain Compressor → Width Control
Master: Gentle EQ → Limiter → True Peak -1 dBFS

Vlog/Entertainment Videos

Voice: Natural, present, slightly intimate
Music: More prominent, sets mood/energy
Effects: Frequent, enhance story

Mix Ratios:
├─ Voice: -6 dBFS peak, -14 LUFS
├─ Music: -15 dBFS peak, -20 LUFS (6 dB below voice)
├─ Effects: -8 dBFS peak (frequent)
└─ Master: -14 LUFS

Processing Chain:
Voice: Light compression, natural EQ, subtle reverb
Music: More prominent, fills sonic space
Master: More aggressive limiting (catch-attention)

Podcast/Interview

Voice: Warm, intimate, conversational
Music: Intro/outro only
Effects: Minimal transitions

Mix Ratios:
├─ Voice 1: -3 dBFS peak, -16 LUFS (balanced)
├─ Voice 2: -3 dBFS peak, -16 LUFS (matched)
├─ Music: -12 dBFS peak (intro/outro only)
└─ Master: -16 LUFS (podcast standard)

Processing Chain:
Voice: Heavy compression (broadcast style), warm EQ, no reverb
Music: Minimal processing, clean
Master: Consistent loudness throughout

Cinematic/Dramatic

Voice: Dynamic, emotional range preserved
Music: Score-like, integral to emotion
Effects: Rich, immersive soundscape

Mix Ratios:
├─ Voice: -6 to -1 dBFS peak (dynamic)
├─ Music: -10 dBFS peak, -18 LUFS (prominent)
├─ Effects: -8 dBFS peak (layered)
└─ Master: -16 LUFS (preserve dynamics)

Processing Chain:
Voice: Light compression (preserve dynamics), EQ for character
Music: Full frequency spectrum, cinematic space
Master: Preserve dynamics, gentle limiting only

Before you install

  • Read the whole file first. Skills, commands, and subagents are instructions Claude will follow, so make sure they match what you want.
  • Check which tools, scripts, or MCP servers it uses. Local servers and scripts run with your permissions.
  • Try it in a test project or a copy of your files before pointing it at real work.
  • Pin the version you tested, and review changes before updating.
  • Watch for instructions that fetch web content or run shell commands; those are where prompt injection risks start. See our prompt injection guide.

FAQ

What is Audio Mixer?

Audio Mixer is a subagent for Claude Code and Claude Cowork from the jeremylongshore/tons-of-skills-marketplace repository on GitHub. Analyzes audio tracks and prescribes a complete mixing workflow — EQ, compression, noise reduction, sidechain ducking, and platform-specific loudness targets — for broadcast-quality results. Use when mixing tutorial or vlog audio. Trigger with \"mix my audio\", \"fix my voice track\".

How do I install Audio Mixer in Claude Code?

Download audio-mixer.md from the repository. Save it to ~/.claude/agents/ to use it in every project, or to .claude/agents/ inside one project to share it through version control. Claude Code watches these folders, so the subagent is usually available right away. Ask Claude to use it by name, or @-mention it to make sure it runs.

Can I use Audio Mixer in Claude Cowork?

Cowork loads subagents through plugins. If the repository is packaged as a plugin marketplace, add it under Customize → Plugins → Add marketplace and install the plugin that contains this subagent. Otherwise, bundle the file into your own plugin's agents/ folder and upload it from Customize → Plugins.

Is Audio Mixer safe to install?

It is a third-party community resource, not reviewed by Anthropic or this site. Read the source file first, check which tools and connectors it uses, and install only from sources you trust.

Similar resources

Browse all skills, subagents, and plugins →

Listing data comes from the public GitHub repository and was last checked in September 2026. Excerpts are © their authors and shared under MIT. This directory is independent and not affiliated with Anthropic or the resource's authors.