A
licenseA
qualityD
maintenanceAn MCP server that enables LLMs to generate spoken audio from text using OpenAI's Text-to-Speech API, supporting various voices, models, and audio formats.
1
6
1
MIT
mcp-speak-when-done
by j3k0
Uses OpenAI's TTS API (or compatible) to convert text summaries to speech, with configurable voice and speed.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@mcp-speak-when-doneExplain the water cycle briefly."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
mcp-speak-when-done
An MCP server that makes AI agents speak a brief summary of every response out loud.
When installed, the agent sees a speak_when_done tool with instructions to call it at the end of every response with a 1-3 sentence spoken summary.
Install
uvx mcp-speak-when-doneClaude Desktop / Claude Code
Add to your MCP configuration:
{
"mcpServers": {
"speak-when-done": {
"command": "uvx",
"args": ["mcp-speak-when-done"],
"env": {
"OPENAI_API_KEY": "your-api-key"
}
}
}
}Works with any OpenAI-compatible TTS API. The provider is auto-detected from your API key:
Key prefix | Provider | Default model | Default voice |
| Groq | canopylabs/orpheus-v1-english | troy |
(other) | OpenAI | tts-1 | alloy |
Requirements
One audio player must be installed: ffplay (from ffmpeg), mplayer, or vlc.
Related MCP server: speaches-mcp
Configuration
All settings are optional environment variables:
Variable | Description | Default |
| API key (required) | — |
| Voice name | auto-detected from key |
| Speech speed |
|
| TTS model | auto-detected from key |
| API endpoint | auto-detected from key |
| Retry count |
|
| Request timeout (s) |
|
Remote Use (SSH + SSE)
If you run Claude on a remote server but want audio on your local machine:
1. On your local machine (has speakers + API key):
OPENAI_API_KEY="your-key" mcp-speak-when-done --transport sseThis starts an SSE server on port 8000 (override with FASTMCP_PORT).
2. SSH tunnel from the remote server to your local machine:
ssh -R 8000:localhost:8000 remote-server3. On the remote server, configure Claude with proxy mode:
{
"mcpServers": {
"speak-when-done": {
"command": "uvx",
"args": ["mcp-speak-when-done"],
"env": {
"SPEECH_PROXY_URL": "http://localhost:8000/sse"
}
}
}
}No API key needed on the remote side. If your local machine is off, the tool silently returns success — Claude keeps working normally.
Variable | Description | Default |
| SSE server URL | — (unset = direct mode) |
| Proxy timeout (s) |
|
License
GPL-3.0-or-later
Available Tools
1 toolspeak_when_doneA
Speak a brief summary of your response out loud. Call this at the end of EVERY response. Summarize what you said in 1-3 short sentences — shorter is better. If your response is a question, speak the question only, not the suggested answers. Keep it natural and conversational.
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| text | Yes | ||
| voice | No | alloy | |
| speed | No |
Output Schema
ParametersJSON Schema
| Name | Required | Description |
|---|---|---|
| result | Yes |
TDQS
A4.3/5.0
Behavior5/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. It transparently describes the tool's behavior: it speaks a summary out loud, is conversational, and should be called at the end. No contradictions.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Description is clear and front-loaded with the core action. It consists of four sentences, each adding value. However, could be slightly more concise by combining the second and third sentences.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With no param explanations and no output schema needed, the description covers the usage intent well but lacks details on parameters and potential limitations like language or audio length, which would help with complete context.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%. The description does not explain the parameters (text, voice, speed) at all. It only describes what the tool does in general terms, leaving the agent without guidance on how to populate the fields.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states the tool speaks a brief summary out loud at the end of every response. It specifies the verb 'speak' and the resource 'summary of your response', with clear usage context.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines5/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly instructs to call at the end of EVERY response, and provides guidance on content: summarize in 1-3 sentences, shorten if possible, and speak only the question if the response is a question. No sibling tools to differentiate.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
1 tool update
v1.0.0- First observed
speak_when_done
TDQS
A4.5/5.0
Disambiguation5/5
Only one tool exists, so there is no possibility of confusion or overlap between tools.
Naming Consistency5/5
The single tool name 'speak_when_done' is clear, descriptive, and follows a natural verb_temporal pattern.
Tool Count5/5
The server is narrowly scoped to speaking a summary when done, so one tool is perfectly appropriate and not thin.
Completeness5/5
The tool fully covers the server's stated purpose of providing a spoken summary; no additional tools are needed.
Maintenance
ActivityInactive
ResponsivenessNo issues
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
AI voice generation: text-to-speech and voice cloning from any MCP client.
MCP server for Text-to-Speech
An MCP server that integrates with Discord to provide AI-powered features.
Official MCP server for Agentwork — delegate tasks to AI agents with human-in-the-loop
Related MCP Servers
- FlicenseCqualityCmaintenanceAn MCP server that exposes speech-to-text and text-to-speech capabilities using a local speaches instance, allowing AI assistants to transcribe audio and generate speech.2-
- FlicenseNot gradedqualityDmaintenanceAn MCP server that lets AI assistants send spoken audio notifications using high-quality AI voices, so you don't have to stare at the screen waiting for long tasks to finish.-
- FlicenseNot gradedqualityDmaintenanceThis MCP server enables Claude to speak summaries, announcements, and explanations aloud using text-to-speech — right from your terminal.-
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/j3k0/mcp-speak-when-done'
If you have feedback or need assistance with the MCP directory API, please join our Discord server