The moment it happens

Turn a video into a summary Doc

Send a video link and get a summary and social posts in a Google Doc.

Runs: The moment it happens
Apps: Google Docs
AI: Yes, uses the built-in AI allowance
Access: read+write

Send this to your assistant

Create a ClickRuntime automation: when I send a YouTube link to this link, get the transcript, write a summary and three social posts from it, and save them as a Google Doc.

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 content creator watches hours of conference talks and interviews for research, but a one-hour video yields maybe four useful points. Taking notes means pausing, rewinding and typing. A busy founder wants the gist of a long lecture without sitting through it, and a marketer wants to turn a webinar into a blog post but is not going to transcribe sixty minutes of speech by hand.

You paste a video link into a ClickRuntime trigger. It fetches the transcript over HTTP and its built-in AI writes a summary, a blog article or a translation, as you choose. It then creates a Google Doc containing the result, so you have something ready to read, edit or publish.

Podcasters, course creators and researchers use it to reuse spoken content in written form.

What you get out of it

Hours of video become minutes of reading
A summary gives you the main points of a long talk. You decide quickly whether to watch the whole thing, and you still get the substance when you do not have the time.
Webinars become blog posts
The AI turns the spoken content into an article, with headings, that you can edit and publish. One recording yields a written asset, which extends the reach of the original event.
Content reaches other languages
A translation option makes talks in one language usable by teammates or customers who speak another. That is faster and cheaper than commissioning a transcript and translation separately. It is a convenient way to share the content with everyone on a team.
Searchable text beats scrubbing a timeline
Once the content is in a Doc, you can search for a name or a number. Finding a half-remembered quote in text takes seconds, while finding it in a video takes ages.
The Doc is ready to share
The result lands in Drive as a normal Google Doc. You can comment on it with colleagues, share the link, or paste the text into your own system without any file conversion.

How it works

What happens, step by step

When you send a YouTube video link, ClickRuntime receives it straight away.
It fetches the video's transcript.
AI turns the transcript into a summary and ready-to-use social posts.
Everything is saved in a new Google Doc.

Before it runs live

Connect Google Docs
Paste your automation's link into the other app's webhook settings

What you get

RunsThe moment it happens

Turn a video into a summary Docjust nowSucceeded

Google Docs · Video notesSummary: Northwind's CTO explains how they cut cloud costs 30%… Post 1: Three changes that cut our cloud bill by a third 🧵

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 Google Docs 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.

video_transcript_to_summary_or_article_doc.pyexample

from google.oauth2.credentials import Credentials
from googleapiclient.discovery import build
import re
from clickruntime import on_event, credentials, http, ai

@on_event
def handle(event):
    url = (event.json or {})["url"]
    video_id = re.search(r"(?:v=|youtu\.be/)([\w-]{11})", url).group(1)
    # Transcript from a transcript API (YouTube's own captions API only serves your own videos).
    transcript = http.get("https://www.searchapi.io/api/v1/search", params={
        "engine": "youtube_transcripts", "video_id": video_id, "api_key": credentials.secret("SEARCHAPI_KEY")}).json()
    text = " ".join(t["text"] for t in transcript["transcripts"])[:24000]
    out = ai.generate("From this video transcript, write a summary (one paragraph), then three social posts.\n" + text,
                      max_output_tokens=1200).text
    creds = Credentials(credentials.connection("google", "work"))
    docs = build("docs", "v1", credentials=creds, cache_discovery=False)
    doc = docs.documents().create(body={"title": f"Video notes {video_id}"}).execute()
    docs.documents().batchUpdate(documentId=doc["documentId"], body={"requests": [
        {"insertText": {"location": {"index": 1}, "text": f"{url}\n\n{out}"}}]}).execute()
    return {"doc": f"https://docs.google.com/document/d/{doc['documentId']}/edit"}

FAQ

Common questions

Which videos work with this?

Videos that have a transcript available, such as those with captions. Videos with no captions, or with transcripts disabled, cannot be processed. Public videos are the safest choice, since private ones are not accessible to the fetch.

Is the article a copy of the transcript?

No. The AI writes new text based on the content, organizing it into sections. It is still derived from someone else's talk, so credit the speaker and check the source's terms before publishing an article that closely follows it.

How accurate is the summary?

It follows the transcript, which may contain captioning errors, especially in names and technical terms. Check any figure or quotation you plan to reuse against the video, since the AI can condense or smooth over details when it shortens a long talk.

What permissions does it need?

read+write. 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 for each event the app sends.

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.

The moment it happensAI