← Back to Skills Marketplace
Voice Memo Transcribe
by
my12121-beep
· GitHub ↗
· v1.1.0
· MIT-0
85
Downloads
0
Stars
0
Active Installs
3
Versions
Install in OpenClaw
/install voice-memo-transcribe
Description
Transcribe Apple Voice Memos recordings to text, organize content, and save to Apple Notes. Workflow: iPhone Voice Memos → iCloud sync → Mac Voice Memos DB →...
Usage Guidance
This skill appears to do what it says: read your Mac's Voice Memos DB, transcribe audio locally with faster-whisper, and create Notes via AppleScript. Before installing: 1) Understand Full Disk Access grants the terminal broad file-read rights—only grant it if you trust the code and source. 2) faster-whisper may download large model files from the internet; expect network activity and disk usage. 3) Review the three included Python scripts yourself (they are small and readable) or run them manually on a test memo before automating. 4) If you prefer to limit risk, run the scripts in an isolated environment (temporary user account, VM, or container) and verify created Notes content. 5) Backup any important Notes/recordings before bulk operations.
Capability Analysis
Type: OpenClaw Skill
Name: voice-memo-transcribe
Version: 1.1.0
The skill accesses sensitive user data by reading the Apple Voice Memos SQLite database (~/Library/Group Containers/.../CloudRecordings.db) and audio files, which requires Full Disk Access. While the Python scripts (list_memos.py, transcribe.py, extract_transcript.py) appear to be legitimate tools for transcription, the instructions in SKILL.md for saving notes are highly vulnerable to injection. Specifically, the use of unquoted shell heredocs (<<< "$NOTE_BODY") and direct string interpolation in AppleScript (set noteTitle to "<TITLE>") allows content from the transcription to potentially trigger shell or AppleScript execution if the AI agent does not perform rigorous sanitization.
Capability Assessment
Purpose & Capability
Name/description (transcribe Voice Memos → Notes) match the included scripts: listing memos from the Voice Memos DB, extracting embedded transcripts from .m4a, running faster-whisper transcription, and saving notes via AppleScript. Requested tools (ffmpeg, uv, faster-whisper) are appropriate for audio processing and local model runtime.
Instruction Scope
SKILL.md explicitly instructs reading the Voice Memos DB and audio files under ~/Library/Group Containers/... and writing a temporary file to /tmp before invoking osascript to create Notes. These actions are necessary for the described workflow, but granting Full Disk Access to the terminal (required to read the DB) is a broad permission — the instructions correctly call it out.
Install Mechanism
No install spec is provided (instruction-only), and included scripts are plain Python. The skill depends on third-party Python package faster-whisper and the uv runner; those are referenced by the runtime commands but not automatically installed—this is low-risk but means the user will install packages locally. Note: faster-whisper may download model weights from the internet when loading a model.
Credentials
No environment variables or external credentials are requested. The only sensitive permission required is Full Disk Access to read the Voice Memos DB and audio files; that is proportional to the task but worth user attention. There are no hard-coded network endpoints or secret-exfiltration behaviors in the code.
Persistence & Privilege
Skill is not always-enabled and does not request persistent system changes. It does create temporary files in /tmp and uses osascript to write Notes (expected for the stated purpose). It does not modify other skills or system-wide configs.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install voice-memo-transcribe - After installation, invoke the skill by name or use
/voice-memo-transcribe - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.1.0
Added bilingual (EN/CN) documentation, MIT-0 license
v1.0.1
Changed license from MIT to MIT-0 (No Attribution)
v1.0.0
Initial release: list memos, extract Apple transcripts, AI transcription with faster-whisper, save to Apple Notes
Metadata
Frequently Asked Questions
What is Voice Memo Transcribe?
Transcribe Apple Voice Memos recordings to text, organize content, and save to Apple Notes. Workflow: iPhone Voice Memos → iCloud sync → Mac Voice Memos DB →... It is an AI Agent Skill for Claude Code / OpenClaw, with 85 downloads so far.
How do I install Voice Memo Transcribe?
Run "/install voice-memo-transcribe" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Voice Memo Transcribe free?
Yes, Voice Memo Transcribe is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Voice Memo Transcribe support?
Voice Memo Transcribe is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Voice Memo Transcribe?
It is built and maintained by my12121-beep (@my12121-beep); the current version is v1.1.0.
More Skills