speaktome-mcp is an open-source CLI tool that provides a local scaffold for transcribing microphone audio to text using Whisper models and the Model Context Protocol (MCP). It is designed for developers and researchers who require local, privacy-preserving speech-to-text workflows.
speaktome-mcp sits in PulseGate's Frameworks & SDKs category. It focuses on transcribing microphone audio to text locally using Whisper models via a command-line interface. It is built as an open-source project for developers and researchers needing local audio transcription tools. The project is open source (MIT). speaktome-mcp is available on the command line, and it can be self-hosted.
It is developed by alma3lol, and it first shipped in 2026. Among its 5 catalogued features are microphone input, whisper transcription, and local processing. It exposes integrations via an MCP server.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do