Yap

cc.yapappPublished by yapapp.ccv1.0.0Updated Oct 26, 2026

Private on-device speech to text: transcribe audio files and search your Yap dictations. No upload.

VerifiedSTDIODesktop onlyFiles & StorageMedia & Design

Overview

AI-generated overview

Yap runs on-device speech-to-text locally, letting an assistant transcribe audio and video files and search your Yap dictation history.

What you can do
  • Transcribe local audio and video files of any length, with automatic language detection among 25 European languages, optional start-time stamps and cleanup.
  • Search the dictation history kept by the Yap app on this computer, newest first, read-only.
  • Download and verify the speech model ahead of the first transcription, or check its status.
When to use it
Useful when you want an assistant to turn recordings, voice memos or interviews into text, or to look up what you previously dictated, without sending audio to a cloud service.
Requirements
A local stdio process started via npx or the packaged installer; Node.js 20 or newer (22.13+ for dictation search); macOS, Windows x64 or Linux x64/arm64. The first transcription downloads a roughly 670 MB speech model from Hugging Face; the cache location can be changed with YAP_MCP_CACHE. No account or API key.
Before you install
The first run downloads a large model over the network. Dictation search reads the Yap app's local history database and returns matching text to the assistant you are using, so that text leaves your machine like anything else you show it. Audio files are read from the paths you give, so the assistant can access any file path it is pointed at.

Installation

In SourceWeft

  1. Open Yap in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

Yap MCP: private, on-device speech to text for AI assistants

Give Claude, Cursor, VS Code, Windsurf or any MCP client the ability to transcribe audio files on your own computer, and to search what you dictated with the Yap app. No upload, no API key, no account.

Yap MCP runs the same speech engine as the Yap dictation app: NVIDIA Parakeet TDT v3 through sherpa-onnx, on your CPU. Audio never leaves your machine; the only network request is a one-time, checksum-verified download of the speech model (about 670 MB) from Hugging Face.

Tools

ToolWhat it does
transcribe_audioTranscribes a local audio or video file of any length: WAV, MP3, M4A/AAC, MP4, FLAC, OGG, Opus, WebM, AIFF, CAF and more. Detects the language automatically among 25 European languages. Optional start-time stamps per passage and Yap's cleanup (capitalization, punctuation, "um" removed).
search_dictationsSearches the dictation history the Yap app keeps on this computer (Mac and Windows), newest first. Read-only.
prepare_speech_modelDownloads and verifies the speech model ahead of the first transcription, or reports its status.

Ask your assistant things like "transcribe ~/Downloads/interview.m4a with timestamps", "summarize the voice memo on my desktop", or "what did I dictate about the budget this week?".

Install

Requires Node.js 20 or newer (22.13+ for search_dictations). macOS (Apple Silicon and Intel), Windows x64 and Linux x64/arm64.

Claude Desktop, one click: download yap.mcpb and open it (macOS and Windows). Or add to claude_desktop_config.json:

json
{  "mcpServers": {    "yap": { "command": "npx", "args": ["-y", "github:founden-bot/yap-mcp"] }  }}

Claude Code:

sh
claude mcp add yap -- npx -y github:founden-bot/yap-mcp

Claude Code plugin: /plugin marketplace add founden-bot/yap-mcp, then /plugin install yap@yap. The plugin runs the server from its own folder (node ${CLAUDE_PLUGIN_ROOT}/src/index.js) with the dependencies pinned in package-lock.json, and adds the transcribe-recordings skill.

Gemini CLI: gemini extensions install https://github.com/founden-bot/yap-mcp.

Cursor, Windsurf, VS Code, Cline, Zed and other clients: add a stdio server with command npx and arguments -y github:founden-bot/yap-mcp.

The first transcription downloads the model once (a few minutes on a typical connection) and answers with the progress while it does; after that, everything runs offline. Transcription runs about ten times faster than real time on a modern laptop, so an hour of audio takes about six minutes.

In the terminal

The same engine as a command: npx -y -p github:founden-bot/yap-mcp yap-transcribe memo.m4a prints the transcript (add --timestamps for start times, several files at once are fine).

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.

Privacy

  • Audio is read from the path you give, decoded in memory and discarded. Nothing is uploaded, logged or stored.
  • search_dictations opens the Yap history database read-only and returns only the dictations that match; that text then goes to the assistant you are using, like anything else you show it.
  • Settings: YAP_MCP_CACHE moves the model cache (default: ~/Library/Caches/yap-mcp on macOS, %LOCALAPPDATA%\yap-mcp on Windows, ~/.cache/yap-mcp on Linux). On Windows, a model already downloaded by the Yap app is reused.

Dictate instead of type

Yap MCP handles recordings. To speak into any app as you work (your editor, Slack, email, the Claude and ChatGPT apps), use Yap: hold a key, talk, and the text appears where your cursor is, transcribed on your computer.

License

MIT for this code. The speech model is NVIDIA Parakeet TDT 0.6B v3 (CC-BY-4.0), ONNX conversion by the sherpa-onnx project (Apache-2.0).

Made by Yap, O-mega Enterprise Inc. Questions: [email protected]

Source: README.md at commit ebb20c9

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v1.0.0LatestOct 18, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts