apple-voice-memo-mcp — MCP server for Claude Code
Lets an AI assistant reach Apple Voice Memos on macOS: list recordings, pull audio, read existing transcripts and generate new ones. Handy if you dictate notes.
claude mcp add apple-voice-memo-mcp -- npx -y apple-voice-memo-mcpWhat apple-voice-memo-mcp does
The server reads the Voice Memos database and the .m4a files stored next to it. Through the list_voice_memos, get_voice_memo, get_audio, get_transcript and transcribe_memo tools an agent can browse recordings with metadata, return an audio path or base64 data, extract a transcript, and produce a fresh one with SFSpeechRecognizer.
Apple keeps transcripts inside the .m4a file itself, in an MPEG-4 atom named tsrp. There are no separate transcript files — the server parses that atom. When a memo has none, transcribe_memo generates one; the language defaults to en-US.
You need macOS Sonoma 14.0 or later and Node.js 18+. Grant Full Disk Access to the terminal or app that launches the server, otherwise the database stays unreadable. The Voice Memos app has to have been opened at least once. Speech recognition asks for its own permission the first time. If native bindings fail on better_sqlite3.node, run npm rebuild better-sqlite3.
What it helps with
- find one voice memo by title among many recordings
- pull a transcript Apple already generated
- create a transcript for a memo that has none
- hand the audio file to an agent as a path or base64
- list recordings with dates and durations for later work
Example prompts for the agent
- Show my voice memos from the past week
- Get the transcript for the memo titled "Standup" and save it to a file
- Transcribe memo id 12 in Russian
How to install apple-voice-memo-mcp
Platform CLI
claude mcp add apple-voice-memo-mcp -- npx -y apple-voice-memo-mcpPlatform CLI
codex mcp add apple-voice-memo-mcp -- npx -y apple-voice-memo-mcpConfig file
{
"mcpServers": {
"apple-voice-memo-mcp": {
"command": "npx",
"args": [
"-y",
"apple-voice-memo-mcp"
]
}
}
}Config file
{
"servers": {
"apple-voice-memo-mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"apple-voice-memo-mcp"
]
}
}
}Platform CLI
gemini mcp add apple-voice-memo-mcp npx -y apple-voice-memo-mcpStep by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more
Questions about apple-voice-memo-mcp
How do I install apple-voice-memo-mcp in Claude Code?
Run claude mcp add apple-voice-memo-mcp -- npx -y apple-voice-memo-mcp, then check the connection with /mcp.
What does apple-voice-memo-mcp do?
It gives an agent access to macOS Voice Memos: listing recordings, returning audio, extracting stored transcripts, and generating new ones via SFSpeechRecognizer.
Why can't the server find the Voice Memos database?
Full Disk Access is probably missing for your terminal or app. Also make sure the Voice Memos app has been opened at least once.
