Apple Voice Memos Agent Skill

Extract and process transcripts from Apple Voice Memos synced via iCloud.

Installing this skill

You can install this skill into Claude Code, Gemini, Cursor, and other agents that support the Agent Skills format:

npx skills add https://github.com/jessedc/apple-voice-memos --skill apple-voice-memos

If you get the error npx: command not found, you need to install Node first:

brew install node

When using npx, you can select whether the skill should be installed just for one project or made available for all your projects.

Alternatively, you can clone this repository or download a release and install it however you like.

Prerequisites

• macOS with Voice Memos iCloud sync enabled

Using this skill

The skill is called Apple Voice Memos, and can be triggered in Claude Code:

/apple-voice-memos

The skill walks you through three steps:

1. Select — Finds voice memos by recency, title search, or date range, flagging any without a transcript (skips the question when your request identifies a single memo)
2. Extract & process — A subagent pulls the embedded transcript from the selected memo and produces structured notes with narrative summary, detailed notes, asides, and action items — keeping the full transcript out of the main conversation
3. Present — Adds the memo's date, duration, and source file beneath the title and offers to save the notes as a markdown file

You can also trigger the skill using natural language:

Use the Apple Voice Memos skill to summarize my most recent voice memo.

How It Works

Two Python scripts (standard library only, no dependencies):

• extract-apple-voice-memos-metadata — Queries the CloudRecordings.db SQLite database (read-only) for recording titles, dates, durations, and filenames, and reports whether each recording has an embedded transcript. Supports filtering and pagination.
• extract-apple-voice-memos-transcript — Extracts transcript text from the tsrp atom embedded in .m4a files by Apple's on-device transcription. Adds timestamps, removes filler words, and inserts paragraph breaks at natural pauses.

Transcripts are extracted from the .m4a files present on your machine, no audio is processed.

Example prompts

I recorded some thoughts on a walk yesterday, can you transcribe and summarize them?

I have a voice memo from a meeting last week — can you turn it into notes with action items?

I rambled into my phone about a project idea recently, help me make sense of it.

Summarize my latest voice memo and save it as a markdown file, without asking me anything.

Find my voice memo about the kitchen renovation and turn it into notes with action items.

Show me the raw timestamped transcript of my latest memo — don't summarize it, I want the exact wording.

Further Reading

• Unlocking Apple Voice Memo Transcripts by Thomas Countz

Acknowledgements

The original transcript extraction tool is by Tomoki Aonuma, licensed under the BSD Zero Clause License. Source: uasi/extract-apple-voice-memos-transcript.

License

0BSD