# apple-voice-memo-mcp [Health: Active]

**Category:** 🎙️ Speech-to-Text  
**Repository:** https://github.com/jwulff/apple-voice-memo-mcp  
**GitHub Stars:** 8  
**npm Downloads (last month):** 188  
**Views:** 0  
**Installs:** 0  
**Upvotes:** 0  
**Directory Page:** https://allmcps.com/mcp/apple-voice-memo-mcp

## Description
Access Apple Voice Memos on macOS. List, get audio, extract and generate transcripts.

## Tools
Capabilities this server exposes over MCP:

- **list_voice_memos** — List all voice memos with metadata.
- **get_voice_memo** — Get detailed metadata for a specific memo.
- **get_audio** — Retrieve the audio file.
- **get_transcript** — Extract transcript from a memo.
- **transcribe_memo** — Transcribe a memo using SFSpeechRecognizer.

## Claude Desktop Quick Installation
Install path detected from listing signals. Uses `npx` (confidence: high):

```json
"mcpServers": {
  "apple-voice-memo-mcp": {
    "command": "npx",
    "args": ["-y","apple-voice-memo-mcp"]
  }
}
```

## Documentation

## 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.

_Full upstream README: https://allmcps.com/mcp/apple-voice-memo-mcp/readme_