# mcp-speak-when-done

> Use this tool when you need to provide audible feedback to users or enhance accessibility for visually impaired individuals. It solves the problem of silent AI responses by generating spoken summaries of every response using Text-to-Speech (TTS) technology. With input of AI response text and output of spoken audio, it is ideal for use cases requiring real-time audible feedback or screen reader functionality.

Canonical page: https://skillsregistry.net/skills/j3k0-mcp-speak-when-done  
JSON: https://api.skillsregistry.net/v1/skills/j3k0-mcp-speak-when-done

## Description

An MCP server that makes AI agents speak a brief summary of every response out loud using TTS.

## Trust

- **Trust score (0–1):** 0.60
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-05-27

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/na1axgvmxy)
- **Repository:** <https://github.com/j3k0/mcp-speak-when-done>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "j3k0-mcp-speak-when-done"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/j3k0-mcp-speak-when-done` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/j3k0-mcp-speak-when-done/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt