Make Sound FAQs

Question 1

Can I use custom voices for text-to-speech, and are there any limitations?

Accepted Answer

Yes, you can select from a curated list of over 50 supported English and international voices for text-to-speech. Text input is limited to 1000 characters, and while voice validation is in place, the system will gracefully fall back to the default voice if an unsupported one is specified.

Question 2

What is Make Sound and what does it do?

Accepted Answer

Make Sound is an MCP (Model Context Protocol) server for macOS that provides comprehensive sound playback capabilities. It allows AI assistants and other MCP-compatible clients to play system sounds, convert text to speech, and play custom audio files for rich audio feedback.

Question 3

What types of sounds can Make Sound play?

Accepted Answer

Make Sound supports playing 14 built-in macOS system sounds (e.g., Basso, Sosumi), converting text to speech with over 50 customizable voices, and playing custom audio files from disk in various formats like .mp3, .wav, and .aiff.

Question 4

How does Make Sound integrate with AI assistants and other applications?

Accepted Answer

It integrates via the Model Context Protocol (MCP) SDK. This allows AI assistants like Claude Desktop or custom MCP clients to call its exposed tools (e.g., `play_info_sound`, `play_sound`) to trigger specific audio feedback based on task outcomes or user interactions.

Question 5

What are the system requirements for running Make Sound?

Accepted Answer

Make Sound requires macOS as it utilizes native macOS audio commands (`afplay` and `say`). It also needs Node.js 18+ and TypeScript for installation and operation.

Make Sound

소개

주요 기능

사용 사례