Google Maps MCP with Speech Input

What is Google Maps MCP with Speech Input?

Google Maps MCP with Speech Input is a web application that upgrades Google's Basic MCP Maps by adding speech as an input option. It runs locally on Node.js and requires API keys for Gemini and Google Maps.

How to use Google Maps MCP with Speech Input?

Clone the repository, install dependencies with npm install, create a .env.local file containing your GEMINI_API_KEY and MAPS_API_KEY, then run npm run dev. Open the app at http://localhost:5173 in your browser.

Key features of Google Maps MCP with Speech Input

• Speech input for map queries
• Integration with Gemini API for processing
• Uses Google Maps API for mapping data
• Runs locally as a web application
• Built upon Google AI Studio’s Basic MCP Maps

Use cases of Google Maps MCP with Speech Input

• Voice-controlled navigation and location search
• Hands-free map interaction while driving or multitasking
• Accessibility for users who prefer or require speech input

FAQ from Google Maps MCP with Speech Input

How does this differ from Basic MCP Maps?

It adds speech as an input option, allowing users to interact with maps using their voice instead of typing.

What API keys are needed to run the app?

You need both a Gemini API key and a Google Maps API key. These are set in the .env.local file.

How do I run the application?

Follow the “Run Locally” steps: clone the repo, run npm install, create .env.local with your API keys, then execute npm run dev and open http://localhost:5173.

Is this project built from scratch?

No, it is a slight upgrade from Google’s Basic MCP Maps project available on AI Studio Apps.

What are the system prerequisites?

Node.js is required. Windows users need WSL to create the .env.local file