Use This MCP server To

Convert text responses to speech in real-time Enable voice notifications from AI assistants Integrate TTS in chatbots for spoken replies Provide audio feedback in accessibility tools Generate spoken alerts from system messages Create voice-enabled interactive tutorials Support multi-language text-to-speech conversion Automate reading of documents or messages aloud

README

mcp-say

TTS (text-to-speech) MCP Server

What? 🤔

Adds Text-to-Speech to things like Claude Desktop and Cursor IDE.

It registers two tools:

say
elevenlabs

`say`

Uses the macOS say binary to speak the text

`elevenlabs`

Uses the elevenlabs text-to-speech API to speak the text

Getting Started

Install

go install github.com/blacktop/mcp-say@latest

❱ mcp-say --help

TTS (text-to-speech) MCP Server.

Provides a text-to-speech service using the MacOS 'say' command.

Designed to be used with the MCP protocol.

Usage:
  mcp-say [flags]

Flags:
  -h, --help      help for mcp-say
  -v, --verbose   Enable verbose debug logging

Set Claude Desktop Config

{
  "mcpServers": {
    "say": {
      "command": "mcp-say",
      "env": {
        "ELEVENLABS_API_KEY": "********",
        "ELEVENLABS_VOICE_ID": "1SM7GgM6IMuvQlz2BwM3"
      }
    }
  }
}

Test

❱ cat test/say.json | go run main.go --verbose

2025/03/23 22:41:49 INFO Starting MCP server name="Say TTS Service" version=1.0.0
2025/03/23 22:41:49 DEBU Say tool called request="{Request:{Method:tools/call Params:{Meta:<nil>}} Params:{Name:say Arguments:map[text:Hello, world!] Meta:<nil>}}"
2025/03/23 22:41:49 DEBU Executing say command args="[--rate 200 Hello, world!]"
2025/03/23 22:41:49 INFO Speaking text text="Hello, world!"

{"jsonrpc":"2.0","id":3,"result":{"content":[{"type":"text","text":"Speaking: Hello, world!"}]}}

License

mcp-say FAQ

How do I install mcp-say?

You can install mcp-say by cloning its GitHub repository and following the build instructions provided in the README, which includes Go environment setup and running the server.

What text-to-speech engines does mcp-say support?

mcp-say supports multiple TTS engines depending on configuration, enabling flexible voice synthesis options.

Can mcp-say handle multiple simultaneous TTS requests?

Yes, mcp-say is designed to handle concurrent text-to-speech requests efficiently for real-time applications.

How does mcp-say integrate with MCP clients?

mcp-say exposes a standardized MCP server interface that clients can connect to for sending text and receiving audio streams.

Is mcp-say open source and under what license?

Yes, mcp-say is open source and licensed under the MIT License, allowing free use and modification.

Can I customize the voice or language in mcp-say?

Voice and language customization depend on the underlying TTS engine configuration, which mcp-say supports through its flexible setup.

Does mcp-say support streaming audio output?

Yes, mcp-say can stream audio output in real-time to clients for immediate playback.

What platforms does mcp-say run on?

mcp-say is built in Go and can run on major platforms including Linux, macOS, and Windows.