Gemini TTS MCP — Local Setup

This repository contains the Gemini TTS MCP server used by Claude Desktop.

This guide explains how to set it up locally on macOS.

1. Requirements

You need:

• macOS

• Claude Desktop

• Node.js

• npm

• A Google Gemini API key

Related MCP server: MCP Audio Server

2. Clone the Repository

Open Terminal and clone the repository:

git clone YOUR_REPOSITORY_URL

Then enter the project:

cd YOUR_REPOSITORY_NAME

Replace YOUR_REPOSITORY_URL and YOUR_REPOSITORY_NAME with the actual repository information.

3. Check Node.js

Check whether Node.js is already installed:

node --version

Also check npm:

npm --version

If both commands return a version number, you can continue.

If Node.js is not installed, install it before continuing.

4. Install Dependencies

Inside the repository folder, run:

npm install

This installs all dependencies required by the MCP server.

5. Create the .env File

The MCP server needs a Gemini API key.

Inside the project folder, create a .env file:

touch .env

Open it:

nano .env

Add:

GEMINI_API_KEY=YOUR_GEMINI_API_KEY

Replace YOUR_GEMINI_API_KEY with your actual Gemini API key.

Save the file:

CTRL + O
ENTER
CTRL + X

Getting a Gemini API Key

Create a Gemini API key through Google AI Studio:

https://aistudio.google.com/apikey

Do not commit the .env file to Git.

The repository should already contain .env in .gitignore.

6. Test the MCP Server

From inside the project directory, run:

node src/server.js

If the server starts without an error about a missing GEMINI_API_KEY, the setup is working.

The server may not display a normal message and may simply keep running.

This is normal.

Stop it with:

CTRL + C

7. Configure Claude Desktop

Claude Desktop needs to know where the MCP server is located.

The configuration file is:

~/Library/Application Support/Claude/claude_desktop_config.json

You can open it with:

open ~/Library/Application\ Support/Claude/claude_desktop_config.json

If the file does not exist, create it.

8. Find Your Node.js Path

Run:

which node

You will get something similar to:

/Users/YOUR_USERNAME/.nvm/versions/node/v24.15.0/bin/node

Copy the path returned by your Mac.

9. Find the MCP Project Path

Inside the repository folder, run:

pwd

For example:

/Users/YOUR_USERNAME/mcp-servers/gemini-tts-mcp

Your MCP server file will therefore be:

/Users/YOUR_USERNAME/mcp-servers/gemini-tts-mcp/src/server.js

10. Add the MCP Server to Claude Desktop

Add the following to:

claude_desktop_config.json

Example:

{
  "mcpServers": {
    "gemini-tts": {
      "command": "/Users/YOUR_USERNAME/.nvm/versions/node/v24.15.0/bin/node",
      "args": [
        "/Users/YOUR_USERNAME/mcp-servers/gemini-tts-mcp/src/server.js"
      ]
    }
  }
}

Important

Replace both paths with the paths from your own Mac.

You can get them with:

which node

and:

pwd

11. If You Already Have Other MCP Servers

Do not replace your existing configuration.

For example, if you already have:

{
  "mcpServers": {
    "other-server": {
      "command": "..."
    }
  }
}

add gemini-tts alongside it:

{
  "mcpServers": {
    "other-server": {
      "command": "..."
    },
    "gemini-tts": {
      "command": "/Users/YOUR_USERNAME/.nvm/versions/node/v24.15.0/bin/node",
      "args": [
        "/Users/YOUR_USERNAME/mcp-servers/gemini-tts-mcp/src/server.js"
      ]
    }
  }
}

12. Restart Claude Desktop

Completely quit Claude Desktop:

CMD + Q

Then open Claude Desktop again.

13. Verify the MCP Connection

In Claude Desktop, go to:

Settings
→ Developer

You should see:

gemini-tts

The server should show as connected.

The available tools should include:

generate_speech
get_audio_files

14. Test Gemini TTS

Open a new Claude conversation and ask:

Use the gemini-tts MCP server to generate speech.

Generate a test using exactly this text:

"This is a test of the Gemini text to speech setup."

Save the file as:

test-voice

Claude should use the generate_speech tool.

The generated audio should be saved inside the project's:

audio/

folder.

15. Generated Audio

Generated .wav files are stored in:

audio/

For example:

audio/
├── test-voice.wav
├── college-vs-university.wav
└── scampi-vs-shrimps.wav

You can open the audio folder in Finder with:

open audio

16. Default TTS Settings

The MCP server is already configured with the following defaults:

• Voice: Algenib

• Vocal style: subtle smile

• Speaking speed: rapid-fire

• Accent: neutral English

• Style: energetic, natural and clear

• Target format: short-form content such as TikTok and Instagram

No additional configuration is required.

17. Troubleshooting

GEMINI_API_KEY is missing

Make sure the .env file exists inside the repository:

ls -la

You should see:

.env

Check it with:

cat .env

It should contain:

GEMINI_API_KEY=YOUR_GEMINI_API_KEY

Server disconnected

First test the server manually:

node src/server.js

If an error appears, fix that error first.

Also check:

which node

and:

pwd

Then make sure the paths in claude_desktop_config.json are correct.

Claude does not show gemini-tts

Check:

1. The MCP configuration JSON is valid.

2. The Node.js path is correct.

3. The server.js path is correct.

4. .env exists.

5. GEMINI_API_KEY exists in .env.

6. Claude Desktop has been completely restarted.

18. Quick Setup Checklist

• Clone repository

• Open repository in Terminal

• Run npm install

• Create .env

• Add GEMINI_API_KEY

• Run node src/server.js successfully

• Run which node

• Run pwd

• Add gemini-tts to Claude Desktop's MCP configuration

• Restart Claude Desktop

• Check Settings → Developer

• Confirm gemini-tts is connected

• Generate a test voice

Done

Once gemini-tts appears as connected in Claude Desktop, no further setup is required.

Claude can now generate Gemini TTS audio through the MCP server.

### One important change I'd make to your repository

Since **you're giving her the repository**, I'd actually recommend that she clones it into a simple, predictable location, e.g.:

```text
~/mcp-servers/gemini-tts-mcp

Then the setup becomes very easy and your Claude config can follow the same structure on both Macs.

Also, don't put your own .env into the repository. The repository should contain something like:

gemini-tts-mcp/
├── src/
│   └── server.js
├── audio/
├── package.json
├── package-lock.json
├── .gitignore
└── README.md

and each person creates their own .env locally with their own Gemini API key.