process_audio_fileLABSCO SUMMARY
Presets are the reason to use this rather than FFmpeg directly.
Anyone can convert a file with FFmpeg; remembering the right sample rate, bitrate and loudness target for console audio versus a phone is the part that takes a search every time. Naming the target instead is what makes a folder of raw takes into a shippable set in one call — and the queue status tool exists because that call takes a while.
What it is
An FFmpeg front end. Sample rate, bitrate, channels, codec, volume and loudness normalisation are parameters rather than command-line flags, and a preset bundles the right combination for a known target.
What you get
- process_audio_file — one file, with volume, format and effect operations described as an object
- batch_process_audio — a whole directory matched by glob, processed through a concurrent queue
- apply_preset — a named target rather than a set of numbers you have to remember
- list_presets, filterable by game, voice, music or effects
- get_queue_status to see how a long batch is progressing
- Presets for mobile, desktop and console game audio, voice and dialogue, music mastering, sound effects, and one tuned for AI voice output
- Volume work in decibels with loudness normalisation to a target LUFS
- Fades, trims and loops alongside the format conversion
- A standalone command-line mode, so the same processing runs outside an assistant
Requirements
FFmpeg installed and on your PATH — the server is a wrapper and does nothing without it. Node.js 18 or newer. Nothing is published to npm, so you build it from a clone and run npm link, which puts the mcp-audio-tweaker command on your PATH. Paths passed to the tools are absolute, and overwriting an existing output file is off unless you ask for it.
Setup effort
Build from source — git clone https://github.com/DeveloperZo/mcp-audio-tweaker.git
USE CASES
01
Preparing a folder of game audio for a platform
Point it at the directory and apply the preset for the target rather than tuning each file.
02
Cleaning up generated voice output
Run the voice preset so levels and format match the rest of your dialogue.
03
Getting a single file into the right shape
Set sample rate, bitrate, channels and codec as parameters, with a volume adjustment in the same call.
04
Making a set of clips sound consistent
Normalise to a target loudness rather than adjusting each one by ear.
05
Choosing the right target
List the presets for your category and read what each is tuned for.
06
Checking on a batch that is still running
Read the queue status instead of watching the output folder.
5 tools
Listed in project docs. Your client may show a different list.
batch_process_audioapply_presetlist_presetsget_queue_statusBEFORE YOU INSTALL
What to know first
Tools you get
5 tools named in the project's documentation.
Requires
- Node.js 18.0.0 or later
- FFmpeg installed and on your PATH
Where it runs
The documented client runs the server on your machine.
INSTALLATION
Connect your client
Server setup
TERMINAL
git clone https://github.com/DeveloperZo/mcp-audio-tweaker.git
cd mcp-audio-tweaker
npm install
npm run build
npm linkMCP Clients
Claude Desktop
CLAUDE DESKTOP · JSON
{
"mcpServers": {
"audio-tweaker": {
"command": "mcp-audio-tweaker",
"env": {
"AUDIO_TWEAKER_LOG_LEVEL": "info"
}
}
}
}npm link puts the mcp-audio-tweaker command on your PATH. If Claude Desktop cannot find it, use the full path that which mcp-audio-tweaker prints. FFmpeg must be installed and on your PATH too.
