You stop agreeing to scope in the moment and regretting it later. When the client slips in “just a small extra”, a short hint and a ready phrase appear in a small window under your camera. After the call, the action items, your promises and the transcript are on a Meetings page, and you did not write any of it.
When it speaks up
Silence is the default. A tip appears only when one of these fires:
A new request
An ask that looks like a change request.
A promised date or estimate
It never suggests hours. The assignee gives the estimate.
A contradiction
Something said against a recorded decision.
Your own slip
An inaccurate or incomplete answer from you.
Side talk
The other team switches to another language between themselves.
Your turn
Someone calls you by name: your update, ready to read.
What a tip looks like
Built for a small window right under the camera, so your eyes do not wander. 2 to 5 short lines: the gist in your language first, then a ready phrase in the language of the call. Simple sentences, everyday words, no abbreviations.
A tip marked as internal relies on an internal source and is never meant to be repeated to the client.
A call, step by step
- Prep in the same session. Meeting prep, the Notion pages or folder to focus on. The Live Brief of the project starts from it.
- Say “live tips” right before the call. A Terminal window opens and records the microphone and the system audio as 2 separate channels: you and them.
- Ask anything mid-call. “What did we promise on exports?” You get a short answer from the brief and the transcript, and it keeps listening.
- Stop it explicitly. Write “stop” in the chat, close the Terminal window, or let the idle timer ask. Closing Zoom or Meet does not stop the recording.
A client interview gets its own mode that tracks the planned questions and suggests follow-ups.
After the call: notes you did not have to write
A wrap-up in the chat: action items with owners and dates, new requests, your commitments, open questions, and answers worth coming back to. A page in the project’s Meetings database appears by itself, with the transcript and the wrap-up. Next steps (a report, a change request, a risk) are offered, never run without your command.
Why it is built this way
- Local Whisper. Client conversations do not go to a third-party transcription service. The model runs on Apple Silicon. The network is needed once, to download it.
- 2 channels, not 1. Microphone and system audio are captured separately, so the transcript knows who is speaking, and switching headphones does not break the recording.
- Your languages are fixed in advance. Your microphone is recognised only among your own languages, the other side among the languages you allow. Better than auto-detect.
- Files as the interface. The skill (the written instructions Claude follows) and the recorder talk only through a few files: start, stop, status and the transcript itself.
Privacy and etiquette
- Audio is not stored. Recognised phrases go straight to a text file, audio buffers live only in memory.
- Transcripts stay in your project folder. Keep them out of public repositories.
- The Meetings page is internal. The skill never sends anything to the client.
- Tell participants you keep a transcript, as with any note taker. Consent rules differ by country and by contract.
What you need
| Mac | Apple Silicon (M1 or newer), macOS 14.2 or newer |
| Tools | Xcode Command Line Tools, Python 3.10+ |
| Disk | About 2.5 GB for the model and the environment |
| Claude | Claude desktop (Cowork) with a connected folder, the plugin and a project config (the short file about your project) |
| Notion | Optional but recommended: the Live Brief and the page after the call need it |
A model tip: a faster model for everyday calls, the strongest one for interviews and high-stakes calls.
Install, about 15 minutes
Most of the time is the model download. Do it once, after floor 2 works.
1. The tools it needs
If you do not have them yet, paste these into Terminal one at a time (Cmd+Space, “Terminal”). Homebrew itself is on the setup page.
xcode-select --install
brew install python@3.12The first one opens a window. Press Install and wait until it finishes.
2. Put the recorder on your Mac
The recorder lives in the repository you downloaded, not inside the plugin. Ask Claude in a task with the work folder:
copy tools/live-transcriber from ~/work/pm-control-tower to ~/work/Tools/live-transcriber3. Run the installer
This one you run yourself in Terminal, because macOS gives sound permissions only to the person at the Mac:
bash ~/work/Tools/live-transcriber/install.shIt builds a small audio program, installs the speech model (about 1.6 GB) and then tests your sound.
4. Allow the microphone and system audio
During the test macOS asks 2 questions. Answer Allow to both:
- Terminal would like to access the microphone. This is your side of the call.
- Terminal would like to record system audio. This is everyone else on the call.
When the script asks, play any sound (a YouTube video) for 5 seconds.
Missed the pop-ups? Open System Settings, Privacy & Security:
- Microphone: switch on Terminal.
- Screen & System Audio Recording: add Terminal under system audio recording.
5. Check it
Ask Claude:
check ~/work/Tools/live-transcriber/logs/install.log and tell me if the install is OKDone when the log ends with install OK and both the mic and sys peaks are above zero. If sys is zero, most likely nothing was playing during the test. Play a video and ask Claude to run the system audio check from docs/en/17-live-tips.md.
6. Try it on a fake call
In a Cowork task with the work folder and Notion on:
live tips <your project>A “Live transcriber” Terminal window opens by itself. Talk for a minute, then write end live in the chat. Done when you get a wrap-up in the chat and a new page in your Meetings database.