voice-memo-sync

Automate transcription, summarization, and tagging of Apple Voice Memos into Apple Notes.

11|1|Updated Mar 8, 2026
One-click install
npx skills add https://github.com/ying-wen/voice-memo-sync --skill voice-memo-sync
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: voice-memo-sync
Source: https://github.com/ying-wen/voice-memo-sync/tree/main
Command: npx skills add https://github.com/ying-wen/voice-memo-sync --skill voice-memo-sync

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires ffmpeg, python3, whisper-cpp, whisper, yt-dlp, remindctl, summarize, pandoc, ffprobe, curl, textutil, md5, and includes scripts (resource) components.

What problem does it solve?

Voice memos, audio, video, and URLs often exist in isolation, making it hard to derive actionable notes or keep them synchronized across devices. This Skill automates ingestion, transcription (Apple native or Whisper), analysis, and organization into Apple Notes and Reminders, all while keeping data local by default.

Core Features & Use Cases

  • Apple native transcription + Whisper fallback for broad coverage
  • Video and audio processing from YouTube/Bilibili with automatic transcription
  • Auto-create structured notes with tags and Reminders integration
  • End-to-end pipeline: ingestion → transcription → analysis → notes → index

Quick Start

Install the skill using the provided installer and then drop in voice memos or URLs to auto-transcribe, summarize, and save structured notes to Apple Notes.

Frequently Asked Questions about voice-memo-sync

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automatically transcribe Apple Voice Memos and save them to Apple Notes?

You can automatically transcribe Apple Voice Memos and save them to Apple Notes by running a local processing pipeline that ingests iCloud recordings, applies Apple native transcription or Whisper fallback, and outputs structured HTML notes directly into Apple Notes.

Can I extract and transcribe audio from YouTube or Bilibili videos locally?

Yes, you can extract and transcribe audio from YouTube or Bilibili videos locally by providing the URL to the pipeline, which fetches the media and applies Whisper transcription to generate structured text notes.

Do I need ffmpeg and whisper installed to process voice memos?

You need ffmpeg and whisper installed to process voice memos if you require fallback audio decoding and transcription beyond Apple native transcripts, ensuring broad file format coverage and local processing.

What is the best way to turn audio transcripts into actionable Reminders?

The best way to turn audio transcripts into actionable Reminders is to use an end-to-end LLM analysis pipeline that extracts tasks from transcribed text and automatically integrates them into the Reminders app.

Does local voice memo transcription work without an internet connection?

Local voice memo transcription works without an internet connection by leveraging Apple native transcripts and local Whisper processing, ensuring your audio data remains completely on your device by default.