Who it is forA team that mixes English and Chinese, acronyms and product names that transcription keeps getting wrong.
The problemMisheard names and terms make minutes look careless and hard to search later.
The outcomeA glossary and recognized speakers, so names, terms and who said what come out right in future minutes.
What you need first
- A Mac with macOS 14.2 or later, Apple silicon or Intel
- Permissions granted during MeetCap setup (covered in the docs at meetcap.seacen.dev)
- An AI agent such as Claude Code or Codex for agent-driven use cases, or a local model, your own API key, or a compatible agent for minutes
Steps
- Record a meeting with MeetCap
- Review the suggested speaker names, with MeetCap's reasoning, and confirm who is who
- Confirm or correct flagged terms and names so they go into the glossary
- Use the source links on each minutes point to replay anything that may be misheard
- Check that the next recurring meeting picks up where the last one left off
Prompt for your agent
In seacen/meetcap, review my last meeting: confirm the speakers, add <names and terms> to the glossary, replay any lines flagged as possibly misheard, and regenerate the minutes.
Caveat. This card is written from the seacen/meetcap README, not from a test run by Deduped. Before you start, make sure you have a Mac with macOS 14.2 or later, Apple silicon or Intel. Check the repo for newer instructions before you rely on these steps.
Use this in your AI agent
Ask your agent
Using the Deduped MCP, get the setup steps for seacen/meetcap and "Teach MeetCap your team's names and jargon"
Add Deduped to Claude Code once
claude mcp add --transport http deduped https://dedupedai.com/mcp
Every Monday: the 5 hottest repos and exactly how to use them. Free, one email a week, unsubscribe anytime.
Get them freeShare: X LinkedIn Hacker News Email Copy link
Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer