Skip to content
Monopea

Monopea Meetings

The call, written down — on your machine.

Transcription runs in the browser, so the audio does not have to leave the machine. Summaries, actions and who-spoke-when come out of the transcript.

Start freeSee pricing
on this devicetranscriptAnaBenAnaChloéactionsSend revised quote · AnaBook follow-up · Bentalk-time · from the transcriptAnaBenChloé

—

No proprietary file format

6

Agent tools behind this app

1

Approval gate for every outward action

CH · EU

Stored in Switzerland. Processed in the EU.

The Meetings surface, showing a recorded call with a speaker-attributed transcript beside a summary of decisions.
Meetings · a speaker-attributed transcript beside the decisions taken

What you ask → what actually happens

Meetings, in the words people type.

Mechanism, not adjectives: each line is what the agent does when you say it.

“What did we agree on Tuesday?”

Answers from the transcript of that call, and points at the moment it came from.

“Turn the actions into tasks.”

The commitments become tracked tasks with owners, attached to the meeting that produced them.

“Who did most of the talking?”

Talk-time and turn-taking computed from the transcript, not estimated by a model.

Capabilities

What Meetings does.

01

On-device speech

Speech models run in your browser — the audio does not have to leave the machine.

02

Actions become tasks

Commitments turn into tracked tasks with owners, attached to the meeting.

03

Measured, not estimated

Talk-time and turn-taking are computed from the transcript.

04

Invite the notetaker

By e-mail, or by pasting the meeting link.

05

Sharing waits

Emailing a summary leaves the workspace, so it is a proposal unless your threshold covers it.

06

Behind the one gate

Anything outward becomes a proposal with its exact arguments and waits for you.

Tools the agent calls

Real functions, not a chat reply.

Verbatim names from the runtime catalog. Every call is logged; anything outward is a proposal first.

  • meeting__list
  • meeting__read
  • meeting__update_summary
  • meeting__set_task_status
  • meeting__stats
  • meeting__send

Governed

It works on its own. It asks at the door.

Inside the workspace the agent just works. Anything above the one risk threshold you set — and anything that leaves — becomes a proposal with its exact arguments, and waits for you.

How the approval gate works
Proposal · send renewal quotedrafted in the workspacecredentials by {{secret}} onlyabove your threshold → askwaiting…Approveactivity logdispatched

Works with

The rest of the suite, one agent.

Calendar

Availability, conflicts, recurrence and RSVPs — the deepest tool surface in the workspace. Changes land in your calendar where you can see them; the invitations are the part that waits.

Explore Calendar

Channels

Threads, tasks and a living canvas per channel — edited by people and the agent side by side, in the same workspace as the files the work is about.

Explore Channels

Mail

Accounts, threads, attachments and search in the same workspace as your files — the agent works from what it reads, and sending stays a thing you do.

Explore Mail

FAQ

Meetings, answered.

Does my audio leave my computer?
Transcription runs in the browser on your device, so the audio does not have to leave the machine.
Can it email the summary?
Yes, and that is an outward action: it is queued for your approval unless the one autonomy threshold you set covers it.
How is talk-time calculated?
From the transcript — counted, not estimated by a model.
Where is my data kept?
Stored in Switzerland. Processed in the EU. Conversations, memory, documents and encrypted secrets are stored in Zurich; on the Swiss model track, inference stays in Switzerland too.

Hand Meetings its first job.

Open a workspace, give the agent a task, and approve what it proposes. Stored in Switzerland, processed in the EU.

Start freeSee every product