Skip to content
ClickRuntime

Automate Google Gemini

The Google Gemini API handles work that goes beyond text: watching YouTube videos, captioning photos, turning articles into spoken audio, generating images and short videos, and answering with live Google Search results. Plug in your own Google AI Studio key and those jobs can run every day or the moment something arrives. Explain the job to your AI assistant, look over the steps it proposes, and it runs from then on.

Add to ChatGPTAdd to Claude
Works inChatGPTClaudeClaude CodeCursorCodexVS CodeGemini CLIZedopencodeAny MCP client

Try asking

Create a ClickRuntime automation: give me a link I can post image URLs to. For each image, use the Google Gemini API to write a one-line caption and alt text under 125 characters, and email them to me.

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

Ideas

What you can automate in Google Gemini

Video summaries, alt text for images, a daily audio briefing, search-grounded research and generated media, sent to your inbox or Slack. These are ready-made starting points. Anything else you can describe works too.
The moment it happens

Write captions and alt text for images

Every image link you send comes back with a caption and accessible alt text.

See how it works
On a schedule

Get summaries of new YouTube videos

When a channel you follow posts a video, you get five bullet points instead of watching it.

See how it works
Weekly

Get a weekly research brief with sources

Every Monday you get a short brief on your topic built from live Google results, with the links it used.

See how it works
Daily

Get a morning summary of your RSS feeds

New articles from your feeds arrive as one list of bullets, without repeats from earlier days.

See how it works
On a schedule

Get an evening recap of market headlines

After the markets close you get the day's finance headlines in a few bullet points.

See how it works
The moment it happens

Summarise posted text into Slack

Whatever your form or tool sends gets condensed to a few lines in a Slack channel.

See how it works Your own logic

Any other automation you can describe in words

Your own rules, schedule and AI steps with Google Gemini, plus any other app. Describe it and your assistant builds it.

See how to build your own

Build your own

Build any Google Gemini automation you can describe

The ideas above are ready-made starting points, not a fixed list. Describe what Google Gemini should do in your own words, with your conditions, other apps or an AI step, and 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.

For example, ask your assistant

Every day, have Google Gemini read new reviews of my app and group them into bugs, feature requests and praise.

For each image added to a Google Drive folder, have Google Gemini write alt text and save it to a Google Sheet.

When a new PDF invoice arrives in Gmail, have Google Gemini extract the vendor, date and total, add a row to Google Sheets and save the file to Google Drive.

Beyond chat

Have Google Gemini work when you're not in the chat

Connecting Google Gemini to ChatGPT or Claude lets you ask about it while you chat. ClickRuntime handles the part that should happen on its own: checks on a schedule and actions on each new event, set up from the same chat and running after you close it.

Setup

Connect Google Gemini

You create a Google Gemini API key in Google AI Studio and save it in ClickRuntime. No Google sign-in or OAuth consent screen is involved.

Google Gemini

AI / LLM

  1. Open Google AI Studio and go to API Keys.
  2. Click Create API key and choose the Google Cloud project it belongs to. You can also manage the key later in the Google Cloud console under Credentials.
  3. For video generation with Veo, turn on billing for that project.
  4. Save the key as a secret on Connections & secrets in the ClickRuntime dashboard.

Good to know

Google Gemini limits that affect automations

  • The free tier allows only a small number of requests per minute, so busy or bulk automations need a paid project.
  • On the free tier, Google may use your prompts and outputs to improve its products. Use a paid project for anything private.
  • Veo video generation is paid-tier only, and generated files expire after a few days, so download or forward them promptly.
  • Answers grounded in Google Search are billed separately once you pass the free quota.
  • Long videos use a lot of tokens per request.

FAQ

Questions about automating Google Gemini

When is it worth adding a Google Gemini key?
When the job needs images, video, audio, YouTube or live Google Search. Plain text jobs like summaries and classification work with the AI that comes with every ClickRuntime plan, with no key needed.
Can it summarise a YouTube video without downloading it?
Yes. The Google Gemini API accepts a public YouTube link directly, so an automation can check a channel's feed for new uploads and send each link for a summary.
Is my data used for training?
On the free tier, Google may use it. On a paid project it isn't. Pick the project your key belongs to with that in mind.
Does it work with Vertex AI?
Not with this connection. Vertex AI uses a Google Cloud service account rather than an AI Studio API key.
How do automations start?
On a schedule, by checking a feed, or when something posts to a link ClickRuntime gives you. The API itself doesn't push events.
Is this a Google Gemini connector for ChatGPT or Claude?
Not for chatting with Google Gemini data. A chat connector lets your assistant read and change Google Gemini while you're in the conversation. ClickRuntime is for the work that should happen without you: you set up an automation from the chat once, and it keeps running on a schedule or on each Google Gemini event.

Related pages

Keep exploring

Tell your assistant what Google Gemini should do

Free plan. No credit card.

Add to ChatGPTAdd to Claude