Audio Tweaker

You can perform batch audio processing and optimization through a dedicated MCP server that leverages FFmpeg for fast, parameter-based transformations. It enables you to apply volume changes, sample-rate conversions, bitrate adjustments, channel configurations, and a variety of effects across many files, all managed through MCP-compatible clients for streamlined workflows.

How to use

You interact with the MCP Audio Tweaker server from an MCP client to apply presets or custom operations to audio files. Use the dedicated presets for common scenarios such as game audio mobile, desktop, or console targets, or craft your own operation sets to tailor volume, format, and effects for each file. The server is designed to process many files in parallel, providing detailed results and robust error handling so you know exactly what happened to each item in your queue.

How to install

Prerequisites must be satisfied before you install the server.

Install the MCP Audio Tweaker package globally so you can run it from anywhere.

Ensure FFmpeg is installed and accessible from your system PATH.

Follow these concrete steps to set up on your machine.

Additional sections

Configuration governs how the server runs in different environments, including logging levels and the path to the FFmpeg binary if you need a custom setup.

If you encounter issues, the server provides structured error codes to help you pinpoint problems quickly, such as missing input files or FFmpeg not being found.

MCP integration example

To integrate with Claude Desktop, you can register the server as an MCP endpoint so you can trigger processing directly from Claude’s interface.

{
  "mcpServers": {
    "audio_tweaker": {
      "command": "npx",
      "args": ["-y", "mcp-audio-tweaker"],
      "env": {
        "AUDIO_TWEAKER_LOG_LEVEL": "info"
      }
    }
  }
}

Available presets and operations

The server includes predefined configurations for common use cases such as game audio across mobile, desktop, and console targets, as well as specialized presets for ElevenLabs AI voice output and generic voice or music processing.

Commands summary for standalone usage

The server can be used in a stand-alone mode to check prerequisites, process single files, or batch process directories using presets.

Tools and capabilities quick reference

• process_audio_file: Process a single audio file with custom operations
• batch_process_audio: Process multiple audio files in a directory
• apply_preset: Apply a predefined audio processing preset
• list_presets: List all available presets with descriptions
• get_queue_status: Get current status of the audio processing queue

Available tools

process_audio_file

Process a single audio file with custom operations such as volume, format, and effects.

batch_process_audio

Process multiple audio files in a directory with a shared set of operations.

apply_preset

Apply a predefined audio processing preset to a file.

list_presets

List all available presets with their descriptions.

get_queue_status

Retrieve the current status of the processing queue.