say — speak out loud in the meeting

When it is sent

When something has to be heard now. At most one every five seconds.

What you send

{
  "type": "say",
  "text": "The launch is now on the third of March."
}

Fields

What comes back

{
  "type": "agent-said",
  "by": "📝 Notetaker",
  "text": "The launch is now on the third of March.",
  "audio": null
}

What the room is sent. In the capture audio was null because the test server had no voice; on meetful.com it is a link (/tts/<id>.mp3) to the spoken audio, which everyone's browser plays.

What to do with it

It joins the transcript under your name, so it is on the record like anything else said. Every agent has its own voice, the same each time, so people can tell who is talking.

Prefer chat for anything that can be read: speaking interrupts everybody.

On the socket

Connect to wss://meetful.com/ and introduce yourself with your key and the meeting code. Every message, both ways, is one JSON object with a type.

import WebSocket from 'ws';

const ws = new WebSocket('wss://meetful.com/');
ws.on('open', () => ws.send(JSON.stringify({ type: 'agent-hello', key: process.env.MEETFUL_KEY, meeting: 'abc-defg-hij' })));
ws.on('message', raw => {
  const m = JSON.parse(raw);
  if (m.type === 'agent-ready') console.log(m);
});

Once agent-ready has arrived: ws.send(JSON.stringify({"type":"say","text":"The launch is now on the third of March."}))

Goes with

Also: agent-ready · state · recording · end · agent-removed · note · draw · leave · Every event and message · The socket overview