# Sound Vocabulary

Describe a click, ding or whoosh and get a WAV and Web Audio code, named by UCS. CC0. It is free, with no sign-up and no key.

Also known as: sound effect generator, UI sound effects, SFX vocabulary.

## What it does

Apps, games and videos need small sounds: a click, a ding, a whoosh, a coin. Finding one that fits and has a clear license takes longer than it should.

Describe the sound in plain words, such as 'a short soft click for a toggle'. You get a sound that plays in the browser, a WAV file to download and a small JavaScript function that plays the same sound with the Web Audio API, so it costs no asset at all.

Every sound is our own synthesis recipe, named by the Universal Category System (UCS) that sound libraries use, so the file names sort the way an editor expects. Words such as deep, short or bright tweak the sound. Everything is CC0: use it anywhere, no credit needed.

- Turns a plain description into a matching sound effect with a WAV link
- Gives a self-contained Web Audio function, such as playCoinPickup(), for the same sound
- Names every sound by the Universal Category System, with a UCS file name
- Tweaks pitch, length and brightness by word or by number

## Who it is for

Anyone who asks an AI assistant a question like this one: “I need a soft click sound for a toggle in my app.”

## Price

Sound Vocabulary is free to use. There is no sign-up, no account and no API key. Calls are limited to 60 calls a minute per network and 5000 calls a day per server, shared by all callers. Repeat questions are answered from a cache.

## Tools it offers

- `make_sound`: Make a sound effect from a description
- `list_sounds`: List the sound vocabulary by UCS category

## Connect

The MCP server is `https://soundvocab.openkrill.app/mcp` (streamable HTTP). It needs no key.

Claude Code, in one command:

```
claude mcp add --transport http sound-vocab https://soundvocab.openkrill.app/mcp
```

Hermes Agent, in one command that answers its two setup questions (no key, enable all tools):

```
printf 'n\ny\n' | hermes mcp add sound-vocab --url https://soundvocab.openkrill.app/mcp
```

Or add these lines to `~/.hermes/config.yaml`, under an existing `mcp_servers:` key if the file has one. Start a new Hermes session after either step.

```
mcp_servers:
  sound-vocab:
    url: https://soundvocab.openkrill.app/mcp
```

Any other agent: give it this page's Markdown address, `https://tools.openkrill.app/tools/sound-vocab.md`, and ask it to connect Sound Vocabulary.

Paste the address into your assistant once: the [connect steps](https://tools.openkrill.app/#connect) cover Claude, ChatGPT and Cursor, and the [install guides](https://tools.openkrill.app/integrations) show the same steps for each client.

## Job recipes for agents

Step-by-step recipes that walk an agent through 2 jobs with this server's tools:

- Make a sound effect from a description, with `make_sound`
- List the sound vocabulary by UCS category, with `list_sounds`

[Download the recipes as SKILL.md](https://tools.openkrill.app/skills/sound-vocab-jobs/SKILL.md). Save it as `sound-vocab-jobs/SKILL.md` in your agent's skills folder. A connected MCP client gets the same recipes from `prompts/list` on this server.

It is listed under Writing, media and files in the [full tool list](https://tools.openkrill.app/tools). The same facts in plain text are in [llms.txt](https://tools.openkrill.app/llms.txt).

Source: the Sound Vocabulary listing, version 1.0.0. As of 2026-10-18.