Log inSubmit server
Apple Voice Memo MCP logo

Apple Voice Memo MCP

Access and transcribe local Apple Voice Memos on macOS through MCP tools.

InstallRepository
Full README Compare alternatives Embed widget Claim this listing

Install Apple Voice Memo 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": {
    "apple-voice-memo-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "apple-voice-memo-mcp"
      ]
    }
  }
}

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

We couldn’t confirm it starts correctly

The install command started, but didn't respond the way we expected when we tried to talk to it.

npx -y apple-voice-memo-mcp

initialize succeeded but no response to tools/list.

This is an experimental automated check and can have false negatives — missing environment variables, a slow cold install, etc. It doesn’t necessarily mean something’s wrong. Last checked 8d ago.

Overview

Accesses local Apple Voice Memos through the apple-voice-memo-mcp MCP server, including memo metadata, audio, and transcripts. It reads the Voice Memos database and .m4a files on macOS, while transcription uses Apple's SFSpeechRecognizer. Reach for it when an AI assistant needs to search recordings, retrieve audio, read stored transcripts, or create a new transcript. It runs through Node.js and requires Full Disk Access, with Speech Recognition permission needed for generated transcripts.

Use cases

  • Search recordings by title
  • Retrieve memo metadata and audio
  • Extract stored transcripts
  • Generate transcripts with Apple's speech recognition
  • Pass audio to a local transcription workflow

Key features

  • List Voice Memos with metadata
  • Retrieve detailed memo information
  • Return audio paths or base64 data
  • Extract text, JSON, or timestamped transcripts
  • Transcribe recordings with SFSpeechRecognizer
  • Search and paginate memo listings

Tools5

What Apple Voice Memo MCP lets your agent do. Expand a tool for its parameters.

Self-reported~61 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 2d ago

Recent health check succeeded.

8/8 checks healthy over the last 52d

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 8d ago via OSV.dev · apple-voice-memo-mcp (npm)

Adoption & maintenance

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

GitHub stars8Stargazers on the source repository.
npm downloads188Package downloads in the last 30 days.
Last commit15d agoMost recent push to the default branch.
Install checkInconclusiveStarted but did not complete the MCP handshake in our test.
Tools exposed5Callable tools this server registers over MCP.

How Apple Voice Memo MCP works

What apple-voice-memo-mcp MCP server does

The apple-voice-memo-mcp MCP server exposes Apple Voice Memos stored on a macOS computer to compatible AI assistants. It can enumerate recordings, return metadata for an individual memo, provide the underlying audio, extract transcripts already embedded in recordings, and request a new transcription through Apple's speech recognition framework.

The server is intended for local Voice Memos data rather than a separate hosted recording service. It relies on the Voice Memos application having been initialized on the Mac and reads the app's local storage. This makes it suitable for assistants that need to find a recording by title, inspect its duration or date, obtain its audio content, or turn a recording into text.

How it works

Voice Memos stores recording information in a SQLite database under the user's macOS Library group-container directory. The audio files are stored in the same general location as .m4a files. The server queries that database for memo records and uses the selected memo ID for later operations.

Stored transcripts are not separate documents. Apple places them inside the audio file in a custom MPEG-4 atom named tsrp; the server parses that embedded data for transcript retrieval. The get_transcript tool can return text, JSON, or timestamped output. When no usable stored transcript exists, transcribe_memo invokes SFSpeechRecognizer, using en-US by default unless another language code is supplied.

The list_voice_memos tool accepts an optional result limit, pagination offset, and title search term. get_audio can return either a file path or base64-encoded audio data. Memo-specific operations require the memo's ID.

Setup and configuration

Install the package globally with npm or run it directly through npx. MCP clients can start it with the npx -y apple-voice-memo-mcp command. A source checkout can instead launch the built dist/index.js file with Node.js.

The runtime requires macOS Sonoma 14 or later and Node.js 18 or newer. Voice Memos must have been opened at least once. Full Disk Access must be granted to the terminal or desktop application that launches the server so it can read the Voice Memos database. The first use of memo transcription also requires macOS Speech Recognition permission.

Limitations and notes

Automatic transcripts depend on macOS and Voice Memos behavior. On macOS Sequoia or later, opening a memo in the Voice Memos application may trigger automatic transcription. Older macOS versions may not provide that automatic transcript, in which case transcribe_memo can generate one through SFSpeechRecognizer.

If the database cannot be found, verify that Voice Memos has been opened, Full Disk Access is enabled, and iCloud syncing is configured as expected. Native-module errors involving better-sqlite3 may require rebuilding that dependency for the installed Node.js version. The project also identifies whisper-mcp as an option to pair with this server for local transcription workflows.

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 Apple Voice Memo MCP

apple-voice-memo-mcp is an MCP server that connects AI assistants to Apple Voice Memos data on macOS. Its main tools list memos, retrieve memo metadata and audio, extract stored transcripts, and generate new transcripts with Apple's SFSpeechRecognizer. It requires macOS permissions and Node.js to run.

Install it with npm or run it with npx. Use `npm install -g apple-voice-memo-mcp` for a global installation, or configure an MCP client to launch `npx -y apple-voice-memo-mcp`.

It needs Full Disk Access to read the Voice Memos database, and Speech Recognition permission when you use `transcribe_memo`. Grant Full Disk Access to the terminal or application that starts the server.

Use the `transcribe_memo` tool with the memo ID, optionally providing a language code such as `en-US`. The tool uses Apple's SFSpeechRecognizer; stored transcripts can instead be retrieved with `get_transcript`.

Yes, it works with Claude Desktop when added to the client's MCP configuration. Start it with the `npx -y apple-voice-memo-mcp` command, then restart Claude Desktop after saving the configuration.

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 PreviewApple Voice Memo MCP AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/apple-voice-memo-mcp?style=directory)](https://allmcps.com/mcp/apple-voice-memo-mcp)
HTML Embed
<a href="https://allmcps.com/mcp/apple-voice-memo-mcp"><img src="https://allmcps.com/api/badge/apple-voice-memo-mcp?style=directory" alt="Apple Voice Memo MCP on AllMCPs" /></a>