Yap MCP icon

Yap MCP

Yap MCP is a free, open-source MCP server for transcribing local recordings and searching Yap dictation history. It runs recognition on the user’s computer and provides setup instructions for compatible AI clients.

Yap MCP
Yap MCP

Local speech-to-text tools for MCP clients

Yap MCP is an open-source MCP server that lets a compatible AI assistant transcribe local audio or video files and search the dictation history kept by the Yap app on that computer. Recognition runs locally rather than uploading recordings to a transcription service.

The official setup page supplies an npm-based command and client configuration examples. A first transcription downloads the speech model; later recognition can work offline once setup is complete. This is a developer integration package, distinct from the desktop dictation app and the browser audio-to-text page.

Features

Local-file transcription

Use transcribe_audio to transcribe a local audio or video recording, with optional start-time stamps.

Dictation-history search

Use search_dictations to search the local history kept by Yap; the documented search is read-only.

Model preparation

Use prepare_speech_model to download and verify the recognition model before a transcription.

MCP-client setup

Configure the server in supported clients using the official command or client-specific instructions.

Use cases

  • Recording research

    Ask a compatible assistant to transcribe an authorized local recording before summarizing it.

  • Finding a dictated note

    Search the local Yap history for a passage previously dictated on that computer.

  • Preparing offline work

    Download the model ahead of time before relying on recognition without a network connection.

Pros and Cons

Pros

  • Processes recognition locally.
  • Exposes transcription and history search through a standard MCP integration.
  • Includes model preparation and setup documentation.

Cons

  • Initial installation and the model download require connectivity.
  • Requires a compatible client and a supported local Node.js environment.
  • History search can expose personal dictated material to the connected assistant, so client permissions matter.

FAQ

What tools are provided?

The official page lists transcribe_audio, search_dictations, and prepare_speech_model.

Does it need an API key or account?

The setup page describes no upload, no API key, and no account for local recognition.

Which Node.js version is required?

The page states Node.js 20 or newer, with 22.13 or newer needed to search dictations. Follow current platform-specific instructions.

Is it free?

The official page describes Yap MCP as free and open source. A connected AI client can have its own separate service terms and costs.

Quick Facts

Type
Local MCP server
Tools
Transcription, dictation search, and model preparation
Recognition
On the user’s computer
Setup
Node.js and an initial model download
Official page
yapapp.cc/mcp