Voice Status Report
Provides voice status updates using OpenAI's text-to-speech API.
About
This tool is a Model Context Protocol (MCP) server designed to provide voice status updates using OpenAI's text-to-speech API. It enables language models to communicate progress reports and confirmations through short voice messages, enhancing user interaction. Ideal for integration with Cursor or Claude, it allows users to receive real-time audio feedback on task progress and completion.
Key Features
- Offers command line options for customization (ding sound, voice selection, speed control, custom instructions)
- Supports multiple voice options (alloy, ash, coral, echo, fable, onyx, nova, sage, shimmer)
- Configurable speech speed
- Provides a `summarize` tool for easy integration with MCP clients
- Converts text to speech using OpenAI's TTS API
- 3 GitHub stars
Use Cases
- Confirming command execution with audio feedback
- Providing status updates on long-running tasks in code editors like Cursor or Claude
- Delivering real-time progress reports from language models