On a schedule

Get a meeting summary from the transcript

After each recorded meeting you get the decisions and action items, written from the transcript.

Runs: On a schedule
Apps: Zoom
AI: Yes, uses the built-in AI allowance
Access: recording:read:admin

Send this to your assistant

Create a ClickRuntime automation: when a Zoom recording's transcript is ready, summarise the meeting with decisions and action items and email it to me.

Paste it into your assistant. It tells you what it will send or change before it runs live.

Add to ChatGPT Add to Claude

First time? Adding ClickRuntime to your assistant takes about two minutes.

Why use it

Why teams use this automation

A team lead holds back-to-back meetings on Zoom and cannot take notes on all of them. Stakeholders who missed the call ask for a summary and get a vague message a day later, if at all. Zoom stores transcripts as VTT files that are hard to read, with timestamps and speaker labels on every line, so nobody opens them. The meeting happened, but its content is effectively lost.

At each check, Zoom is searched for new transcript files. The VTT is downloaded and the built-in AI turns it into a clear summary with the main points, decisions and action items. You receive the result by email, so the recap is waiting soon after the meeting ends.

Best for people who attend many meetings and want a consistent recap. Because the summary comes from the transcript itself, it reflects what was said, not what someone remembers.

What you get out of it

Meetings leave a usable record
A short summary survives where a 60-minute transcript will not be read. People can recall what was decided months later, and the details do not depend on one attendee's memory.
Absent stakeholders catch up in a minute
Instead of scheduling a call to explain what was said, you forward the summary. Colleagues who missed the meeting catch up in a minute, and everyone's calendar stays a little emptier.
Consistent format every time
Each recap has the same structure, so readers know where to find decisions and action items. Skimming a week of meetings becomes quick, because the layout never changes from one email to the next.
Less time on recaps
Writing a summary after a meeting often takes 15 minutes. Across ten meetings a week, that is hours reclaimed, and the recap is no longer the task that slips when the day gets busy.
Decisions are harder to dispute
A summary written from the transcript is neutral. It reduces arguments about what was agreed, and it gives a fair starting point when two people remember a decision differently. Both people can check the transcript.
Useful for recurring meetings
Weekly check-ins pile up quickly. A summary after each one makes it easy to see how a project moved from one week to the next, and what was promised along the way.

How it works

What happens, step by step

Every 15 minutes ClickRuntime looks at your Zoom recordings from the last two days for any with a finished transcript.
It skips meetings it has already summarised.
For each new one it downloads the transcript, and AI writes a summary that lists the decisions, then the action items with owners.
Each summary arrives as its own email, titled with the meeting topic.

Before it runs live

Connect Zoom

What you get

RunsOn a schedule

Get a meeting summary from the transcripttoday, 9:00Succeeded

Email · Summary: Acme onboarding callDecisions: launch moves to Nov 4. Action items: send revised SOW (Priya, Fri); share test account (Northwind team).

Build your own

Need it to work differently?

This template is a starting point. Copy the prompt and change it, or describe a different automation from scratch, with your own conditions, more apps or an AI step. Your assistant writes it, tests it and runs it on ClickRuntime.

Your own rules
Conditions, thresholds, filters and exceptions, written the way you'd explain them to a colleague.
Any number of apps
One automation can read from one app and update several others. Over 248 apps are ready, and anything with an API works too.
AI where it helps
Summaries, classification, extraction and drafts use ClickRuntime's built-in AI, with no extra key.
On a schedule or on each event
Runs as often as every 5 minutes, or the moment an app sends an event, and keeps track of what it already handled.

Changes you can ask for

Act only on the items that match your own rules, and skip the rest
Change what the AI looks for, or how it writes the result
Add another app, for example also send it to Slack
Combine it with other Zoom steps into one automation

Under the hood

The code that runs this automation

This is the Python script that runs each time the automation starts. Your AI assistant writes it for you when you send the prompt, and you allow each step in your assistant. To change how the automation works, describe the change to your assistant and it updates the script for you. For every function it can use, see the script reference.

ai_meeting_summary_from_transcript.pyexample

from datetime import date, timedelta
from clickruntime import on_trigger, credentials, http, state, ai, notify, report_fetched

@on_trigger
def run(event):
    token = credentials.connection("zoom", "work")
    h = {"Authorization": f"Bearer {token}"}
    done = set(state.get("done") or [])
    since = (date.today() - timedelta(days=2)).isoformat()
    meetings = http.get("https://api.zoom.us/v2/users/me/recordings",
                        params={"from": since}, headers=h).json().get("meetings", [])
    ready = [(m, f) for m in meetings for f in m.get("recording_files", [])
             if f["file_type"] == "TRANSCRIPT" and f.get("status") == "completed" and m["uuid"] not in done]
    report_fetched(len(ready))
    if not ready:
        return {"summary": "Nothing new"}
    for m, f in ready:
        vtt = http.get(f["download_url"], headers=h).text[:60000]
        summary = ai.generate(f"Summarise this meeting transcript. List decisions, then action items with owners.\n\n{vtt}",
                              max_output_tokens=700).text
        notify.email_me(f"Summary: {m['topic']}", summary)
        done.add(m["uuid"])
    state.set("done", list(done)[-500:])
    return {"summarised": len(ready)}

FAQ

Common questions

How is this different from Zoom's own meeting summary?

Zoom's AI Companion summary requires a certain Zoom plan and setup. This works from the transcript file, with a summary format you control, and it does not depend on those features being available. Check results against the transcript.

Does it work if transcripts are in another language?

The AI can summarize transcripts in many languages, and you can ask for the summary in a different language than the meeting. Accuracy follows the quality of the original transcript. The AI can summarize in many languages, and accuracy follows the transcript.

How long after the meeting does the email arrive?

Zoom needs time to process the recording and transcript, and the check runs on a schedule. Expect the email after the transcript becomes available, typically within the hour. Timing depends on Zoom's processing. Long meetings take longer to process.

What permissions does it need?

recording:read:admin. Nothing else in your accounts is used.

Does it need AI?

Yes. It uses ClickRuntime's built-in AI, so you don't need an OpenAI or Anthropic key. Every plan includes a monthly AI allowance.

How many runs does it use?

One run each time it checks. Checks that find nothing new and stop right away aren't counted.

Can I change how it works?

Yes. Describe the change to your AI assistant, for example a different schedule, channel or filter. It updates the automation, tests it and tells you what changed.

Every 15 minutes