Voice Status Report MCP Server

What is Voice Status Report MCP Server?

Voice Status Report MCP Server is a Model Context Protocol (MCP) server that uses OpenAI’s text-to-speech API to convert text into spoken voice messages. It allows language models, such as those in Cursor or Claude code, to communicate progress updates or confirmations audibly to the user. It is designed for developers who want to receive voice status reports while working on tasks away from the screen.

How to use Voice Status Report MCP Server?

You need an OpenAI API key. Configure the server by adding a stanza to your claude_desktop_config.json with the command uvx voice-status-report-mcp-server and the environment variable OPENAI_API_KEY. Optional command line arguments include --ding (play a ding before each message), --voice (choose from voices like alloy, ash, coral, echo, fable, onyx, nova, sage, shimmer; default coral), --speed (speech speed 0.5–4.0; default 4.0), and --instructions (custom voice instructions). Example: voice-status-report-mcp-server --ding --voice nova.

Key features of Voice Status Report MCP Server

• Provides a single summarize tool that converts text to speech.
• Uses OpenAI’s TTS API for high-quality voice output.
• Supports multiple voices (alloy, ash, coral, echo, fable, onyx, nova, sage, shimmer).
• Allows adjustable speech speed (0.5 to 4.0).
• Optional ding sound before each voice message.
• Customizable voice instructions for tone and style.

Use cases of Voice Status Report MCP Server

• Receive spoken progress updates during long-running code tasks.
• Get audio confirmation after a command has been executed.
• Stay informed about agent activity while working away from the screen.

FAQ from Voice Status Report MCP Server

Do I need an API key?

Yes, the server requires an OpenAI API key set as the environment variable OPENAI_API_KEY.

What tools does the server expose?

It exposes one tool: summarize(text: str), which converts the given text into speech and plays it to the user.

Can I change the voice or speech speed?

Yes. Use the --voice and --speed command line options. Available voices include alloy, ash, coral (default), echo, fable, onyx, nova, sage, and shimmer. Speed range is 0.5–4.0.

How do I enable the ding sound before a message?

Pass the --ding flag when starting the server.

Where is the configuration file for Claude Desktop?

On macOS it is located at ~/Library/Application\ Support/Claude/claude_desktop_config.json; on Windows at %APPDATA%/Claude/claude_desktop_config.json.