Telegram + Google Gemini: YouTube Shorts scripts fast
You find a great YouTube video, you know it could become a solid Short, and then you hit the usual wall. Transcript hunting, copy-paste chaos, and that weird moment where you’re rewriting the same idea three times just to make it “Shorts-ready.”
This Gemini script automation hits content creators first, honestly. But social media managers repurposing client videos and small agency owners trying to keep a posting cadence feel the drag too. The outcome is simple: you send a link, you get a usable Shorts script back in Telegram.
Below you’ll see how the workflow pulls a transcript, has Google Gemini shape it into a hook + tight script, and sends it back so you can record (or hand it to someone who will).
How This Automation Works
The full n8n workflow, from trigger to final output:
n8n Workflow Template: Telegram + Google Gemini: YouTube Shorts scripts fast
flowchart LR
subgraph sg0["Parsing Flow"]
direction LR
n0["<div style='background:#f5f5f5;padding:10px;border-radius:8px;display:inline-block;border:1px solid #e0e0e0'><img src='https://flowpast.com/wp-content/uploads/n8n-workflow-icons/telegram.svg' width='40' height='40' /></div><br/>Send Summary"]
n3@{ icon: "mdi:robot", form: "rounded", label: "Parsing", pos: "b", h: 48 }
n5@{ icon: "mdi:brain", form: "rounded", label: "Google Gemini Chat Model", pos: "b", h: 48 }
n6@{ icon: "mdi:robot", form: "rounded", label: "Create Script", pos: "b", h: 48 }
n3 -.-> n6
n6 --> n0
n5 -.-> n6
end
subgraph sg1["Input URL Flow"]
direction LR
n1["<div style='background:#f5f5f5;padding:10px;border-radius:8px;display:inline-block;border:1px solid #e0e0e0'><img src='https://flowpast.com/wp-content/uploads/n8n-workflow-icons/telegram.svg' width='40' height='40' /></div><br/>Input URL"]
n2@{ icon: "mdi:cog", form: "rounded", label: "Make Transcribe", pos: "b", h: 48 }
n1 --> n2
end
subgraph sg2["Flow 3"]
direction LR
n4@{ icon: "mdi:swap-vertical", form: "rounded", label: "Script mapping", pos: "b", h: 48 }
end
%% Styling
classDef trigger fill:#e8f5e9,stroke:#388e3c,stroke-width:2px
classDef ai fill:#e3f2fd,stroke:#1976d2,stroke-width:2px
classDef aiModel fill:#e8eaf6,stroke:#3f51b5,stroke-width:2px
classDef decision fill:#fff8e1,stroke:#f9a825,stroke-width:2px
classDef database fill:#fce4ec,stroke:#c2185b,stroke-width:2px
classDef api fill:#fff3e0,stroke:#e65100,stroke-width:2px
classDef code fill:#f3e5f5,stroke:#7b1fa2,stroke-width:2px
classDef disabled stroke-dasharray: 5 5,opacity: 0.5
class n1 trigger
class n3,n6 ai
class n5 aiModel
classDef customIcon fill:none,stroke:none
class n0,n1 customIcon
The Problem: Turning Long Videos into Shorts Scripts Is Slow
Repurposing should feel like a shortcut. Instead, it turns into a mini project. You grab a link, then you’re bouncing between transcript tools, YouTube captions, and notes apps, trying to pull out the “one point” that will actually work in a 30–60 second Short. Half the time, you end up with a summary that sounds fine on paper but has no hook, no pacing, and no clean ending. Then you rewrite. Again.
The friction compounds, especially when you want to do this more than once a week.
- Getting a transcript often means using a separate tool, then cleaning up messy formatting by hand.
- Shorts scripts need structure (hook, beats, payoff), and most “summaries” don’t give you that.
- When you’re on the go, you can’t easily repurpose from your phone without losing the thread.
- Inconsistent scripts lead to extra edits, which quietly kills your posting rhythm.
The Solution: Send a YouTube Link, Get a Shorts Script Back
This workflow turns Telegram into your “repurpose inbox.” You send a YouTube URL to your Telegram bot, and n8n takes over. First, it retrieves the video transcript via Supadata (a community node that pulls transcripts reliably). Then it packages that transcript into a clean input for an AI prompt. Google Gemini generates a Shorts-optimized script with a title and a tight body that’s easier to read aloud. Finally, the finished script is sent back to you in Telegram, ready to record or tweak.
It starts with a Telegram message. Supadata fetches the transcript, then Gemini shapes it into something performable. A Telegram reply delivers the final script so you’re not digging through tools to find it.
What You Get: Automation vs. Results
| What This Workflow Automates | Results You’ll Get |
|---|---|
|
|
Example: What This Looks Like
Say you repurpose 5 long-form videos a week. Manually, it’s usually about 20 minutes to grab a transcript, skim it, and rewrite a Short script that has a real hook, so call it about 100 minutes weekly. With this workflow, you spend maybe 1 minute sending links in Telegram, then wait a few minutes for processing while you do something else. You’re still reviewing the script (you should), but you’re no longer starting from a blank page.
What You’ll Need
- n8n instance (try n8n Cloud free)
- Self-hosting option if you prefer (Hostinger works well)
- Telegram to receive links and deliver scripts
- Google Gemini to generate Shorts-ready scripts
- Supadata API key (get it from your Supadata dashboard)
Skill level: Intermediate. You’ll connect credentials and install one community node if you self-host.
Don’t want to set this up yourself? Talk to an automation expert (free 15-minute consultation).
How It Works
You send a YouTube URL in Telegram. The workflow begins the moment your bot receives a message containing a link.
The transcript gets pulled automatically. n8n uses the Supadata community node to fetch the transcript, so you’re not copying captions or juggling third-party transcript sites.
Gemini turns raw text into a Shorts script. The workflow assembles the transcript into a clean input, then a Gemini chat model generates a structured output (title plus a script body that’s easier to read aloud).
The script lands back in Telegram. You get the result in the same chat where you sent the link, which means you can capture ideas from your phone and keep moving.
You can easily modify the prompt style to match your brand voice based on your needs. See the full implementation guide below for customization options.
Step-by-Step Implementation Guide
Step 1: Configure the Telegram Trigger
This workflow starts when a Telegram message containing a video ID is received.
- Add the Telegram Link Trigger node as the trigger.
- Set Updates to
message. - Credential Required: Connect your telegramApi credentials in Telegram Link Trigger.
Step 2: Connect Supadata to Fetch the Transcript
The trigger passes the video ID to Fetch Transcript, which retrieves the transcript text.
- Add the Fetch Transcript node and connect it to Telegram Link Trigger.
- Set Operation to
getTranscript. - Set Video ID to
{{ $json.message.text }}. - Credential Required: Connect your supadataApi credentials in Fetch Transcript.
Step 3: Set Up Script Assembly and AI Generation
The transcript is transformed into a single script string and sent to the AI chain for formatted output.
- Add Assemble Script Text and connect it to Fetch Transcript.
- Create a field named full_script with value
{{ $json.content.map(item => item.text).join('\n') }}. - Add Generate Trivia Script and connect it to Assemble Script Text.
- Set Text to
=#background information {{ $json.full_script }}. - Enable the output parser in Generate Trivia Script (it uses Structured Output Parser).
- Attach Gemini Chat Engine as the language model for Generate Trivia Script.
- Credential Required: Connect your googlePalmApi credentials in Gemini Chat Engine.
Structured Output Parser is an AI sub-node. Add any required credentials to Generate Trivia Script (the parent), not the parser itself.
Step 4: Configure Telegram Output Delivery
The generated title and script are sent back to the originating Telegram chat.
- Add Dispatch Summary and connect it to Generate Trivia Script.
- Set Text to
{{ $json.output.title }} {{ $json.output.script }}. - Set Chat ID to
{{ $('Telegram Link Trigger').item.json.message.chat.id }}. - Credential Required: Connect your telegramApi credentials in Dispatch Summary.
Step 5: Test and Activate Your Workflow
Verify the end-to-end flow before enabling it in production.
- Click Execute Workflow and send a Telegram message with a valid video ID to trigger Telegram Link Trigger.
- Confirm that Fetch Transcript returns transcript content and Assemble Script Text outputs full_script.
- Check that Generate Trivia Script returns structured output with
titleandscript. - Verify the final message appears in Telegram via Dispatch Summary.
- When successful, switch the workflow to Active to run continuously.
Common Gotchas
- Telegram bot credentials can expire or get misconfigured. If messages stop triggering, check the Telegram Trigger node credentials and your bot token in BotFather first.
- If you’re using Wait nodes or external rendering, processing times vary. Bump up the wait duration if downstream nodes fail on empty responses.
- Supadata or Gemini keys can fail due to permissions or rate limits. If transcript fetches come back empty, verify your Supadata API key and check its usage logs before changing the workflow.
Frequently Asked Questions
About 30 minutes if you already have your API keys.
No. You’ll mostly paste in credentials and edit a prompt if you want a different tone.
Yes. n8n has a free self-hosted option and a free trial on n8n Cloud. Cloud plans start at $20/month for higher volume. You’ll also need to factor in Gemini API usage plus Supadata transcript lookups.
Two options: n8n Cloud (managed, easiest setup) or self-hosting on a VPS. For self-hosting, Hostinger VPS is affordable and handles n8n well. Self-hosting gives you unlimited executions but requires basic server management.
Yes, and it’s the best part. You’ll edit the prompt in the Google Gemini node to match your voice (more energetic, more educational, more “storytime,” whatever works). Common customizations include adding a stronger first-line hook, forcing a specific length like 120–160 words, and asking for on-screen captions cues. If you want to swap AI providers, you can replace the Gemini chat model node with an OpenAI node and keep the rest of the flow the same.
Usually it’s the bot token or a missing permission in the Telegram credentials you saved in n8n. Regenerate the token in BotFather if you suspect it leaked or was rotated, then update the Telegram Trigger and send node to use the new credential. Also check that your workflow is active and that you are messaging the correct bot chat.
If you self-host, there’s no hard execution limit (it mostly depends on your server) and most small teams run dozens of videos a day without issues.
Often, yes, for this use case. The transcript step relies on a community node, and n8n is simply more comfortable when you need “fetch data, transform it, then run an AI chain” logic. You also get a self-hosted option, which matters once you start processing lots of links. Zapier or Make can be quicker for very simple workflows, but you may hit limits as soon as you add branching, retries, or more complex AI prompting. Talk to an automation expert if you want a quick recommendation based on your volume.
Once this is running, turning a random YouTube find into a record-ready Short stops being a chore. You’ll feel the difference after the first few links.
Need Help Setting This Up?
Our automation experts can build and customize this workflow for your specific needs. Free 15-minute consultation—no commitment required.
