Log inSubmit server
Yap MCP logo

Yap MCP

Transcribes local media offline with Parakeet TDT v3 and searches Yap dictation history through MCP.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install Yap MCP

Pick your client, then add it in one click or paste the config.

STDIONode.js
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "yap-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "github:founden-bot/yap-mcp"
      ],
      "env": {
        "YAP_MCP_CACHE": "YOUR_VALUE_HERE"
      }
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

Values are written into the snippet above so you can paste it as is. They never leave your browser.

Install not yet sandbox-tested— we haven't run this command through our automated sandbox yet. Not a red flag; we're working through the catalog.

Overview

Yap MCP MCP server gives AI assistants local speech-to-text using NVIDIA Parakeet TDT v3 through sherpa-onnx. It transcribes audio and video on the host CPU, detects 25 European languages, and can add passage timestamps or clean up punctuation and filler words. It also searches Yap dictation history on macOS and Windows and can prepare the speech model before use. Reach for it when recordings must stay on the computer or when an assistant needs to work with previously dictated text.

Use cases

  • Transcribe interviews and voice memos from local files
  • Generate timestamped transcripts for recorded meetings
  • Search Yap dictation history for previously spoken notes
  • Summarize recordings without uploading their audio
  • Prepare the speech model before an offline transcription session

Key features

  • Local CPU transcription for audio and video files
  • Automatic detection across 25 European languages
  • Optional passage timestamps and text cleanup
  • Read-only search of Yap dictation history
  • Checksum-verified speech model download
  • Terminal transcription for one or more files

Tools3

What Yap MCP lets your agent do. Expand a tool for its parameters.

Self-reported~136 tokens of context

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked Today

Recent health check succeeded.

5/5 checks healthy over the last 16d

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 16d ago via OSV.dev · github:founden-bot/yap-mcp (npm)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

Last commit15d agoMost recent push to the default branch.
Tools exposed3Callable tools this server registers over MCP.
Directory activity2 viewsConfig copies, upvotes, and views on AllMCPs.

How Yap MCP works

What Yap MCP does

Yap MCP connects MCP-compatible assistants to two local speech workflows: transcribing recordings and searching dictation history created by the Yap app. The transcription tool accepts local audio or video files, including WAV, MP3, M4A, AAC, MP4, FLAC, OGG, Opus, WebM, AIFF, and CAF. Files can be any length.

Speech recognition uses NVIDIA Parakeet TDT v3 through sherpa-onnx and runs on the computer’s CPU. Automatic language detection covers 25 European languages: English, German, French, Spanish, Italian, Portuguese, Dutch, Polish, Russian, Ukrainian, Swedish, Danish, Finnish, Czech, Slovak, Hungarian, Romanian, Bulgarian, Greek, Croatian, Slovenian, Latvian, Lithuanian, Estonian, and Maltese.

How it works

The assistant calls transcribe_audio with a local file path. The server reads and decodes the audio in memory, then returns the transcript. Optional passage start times can be included, and Yap’s cleanup can add capitalization and punctuation while removing “um”. Audio is discarded after processing; it is not uploaded, logged, or stored.

The first transcription downloads the speech model from Hugging Face and verifies it with a checksum. The download is approximately 670 MB and is the only network request described for normal operation. Later transcriptions run offline. On a modern laptop, processing is reported at roughly ten times faster than real time.

search_dictations reads the Yap app’s history database in read-only mode and returns matching entries newest first. Matching text is then available to the assistant, just like other content shared with that assistant.

Setup and configuration

Node.js 20 or newer is required. search_dictations requires Node.js 22.13 or newer. Supported platforms include macOS on Apple Silicon or Intel, Windows x64, and Linux x64 or arm64.

For a standard MCP installation, configure a stdio server with command npx and arguments -y github:founden-bot/yap-mcp. Claude Desktop also supports the downloadable yap.mcpb package. Claude Code can add the server with claude mcp add, and Gemini CLI can install the repository as an extension. A Claude Code plugin is available and includes a transcribe-recordings skill.

The YAP_MCP_CACHE variable changes where the model is stored. Defaults are ~/Library/Caches/yap-mcp on macOS, %LOCALAPPDATA%\\yap-mcp on Windows, and ~/.cache/yap-mcp on Linux. On Windows, an existing model downloaded by the Yap app is reused.

Tools and capabilities

  • transcribe_audio processes local audio or video, detects the spoken language, and optionally returns timestamps and cleaned text.
  • search_dictations searches Yap dictation history without modifying it.
  • prepare_speech_model downloads and verifies the model in advance or reports its current status.
  • The same transcription engine can also be run from a terminal with yap-transcribe, including timestamp output and multiple input files.

Limitations and notes

Processing is local, but the initial model download requires network access. The model is downloaded once before offline transcription is available. Search history is tied to the Yap app database on the computer and is read-only. The speech model is NVIDIA Parakeet TDT 0.6B v3 under CC-BY-4.0; its ONNX conversion is from sherpa-onnx under Apache-2.0, while the server code is MIT-licensed.

Read the full README View source on GitHub

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about Yap MCP

Yap MCP is an MCP server that connects AI assistants to local audio and video files and the Yap app’s dictation history. Its main tools transcribe recordings, search dictations, and prepare the Parakeet TDT v3 speech model. Processing runs on the computer, with no audio upload or API key required.

Install it as a stdio server using `npx -y github:founden-bot/yap-mcp` as the command and arguments. Claude Desktop can open the downloadable `yap.mcpb`; Claude Code and Gemini CLI have dedicated installation commands, and other named clients use the same stdio configuration.

Yes, Yap MCP works with Cursor through a stdio server configuration. Set the server command to `npx` and pass `-y github:founden-bot/yap-mcp` as its arguments, then use the assistant to transcribe local recordings or search available Yap dictations.

Yes, transcription runs offline after the speech model has been downloaded once. The initial setup needs a network connection to download and checksum-verify the approximately 670 MB model from Hugging Face; subsequent audio processing stays on the computer.

Related MCP servers

All in Speech-to-Text All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewYap MCP AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/yap-mcp?style=directory)](https://allmcps.com/mcp/yap-mcp)
HTML Embed
<a href="https://allmcps.com/mcp/yap-mcp"><img src="https://allmcps.com/api/badge/yap-mcp?style=directory" alt="Yap MCP on AllMCPs" /></a>