January 22, 2026

YouTube to Google Sheets, trend ideas ready to use

Lisa Granqvist Partner Workflow Automation Expert

Get a free AI assessment → ⬇️ Use template

You find a promising YouTube trend, open six tabs, copy the title, grab a link, try to judge the thumbnail, then lose the transcript somewhere along the way. Do that a few times and your “research session” quietly becomes your whole afternoon.

This YouTube Sheets automation hits content marketers first, honestly. But agency leads building client calendars and solo creators trying to stay consistent feel the same drag. The outcome is simple: trend ideas land in one Google Sheet, already cleaned up, deduped, and expanded with hooks and outlines.

Below you’ll see exactly what this workflow does, what you’ll need, and how the moving parts fit together before you decide to implement it.

How This Automation Works

Here’s the complete workflow you’ll be setting up:

n8n Workflow Template: YouTube to Google Sheets, trend ideas ready to use

Click to explore

flowchart LR

    subgraph sg0["On form submission Flow"]
        direction LR
        n0@{ icon: "mdi:swap-horizontal", form: "rounded", label: "If", pos: "b", h: 48 }
        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/merge.svg' width='40' height='40' /></div><br/>Merge"]
        n2@{ icon: "mdi:database", form: "rounded", label: "Step 1 Results", pos: "b", h: 48 }
        n3@{ icon: "mdi:database", form: "rounded", label: "Find Duplicate Entries", pos: "b", h: 48 }
        n4@{ icon: "mdi:robot", form: "rounded", label: "YouTube Title Generator", pos: "b", h: 48 }
        n5@{ icon: "mdi:robot", form: "rounded", label: "Analyze Thumbnail", pos: "b", h: 48 }
        n6@{ icon: "mdi:database", form: "rounded", label: "Update Rows", pos: "b", h: 48 }
        n7["<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/httprequest.dark.svg' width='40' height='40' /></div><br/>YouTube Video Scrape"]
        n8["<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/httprequest.dark.svg' width='40' height='40' /></div><br/>HTTP Request"]
        n9["<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/form.svg' width='40' height='40' /></div><br/>On form submission"]
        n10@{ icon: "mdi:robot", form: "rounded", label: "Outline Generator", pos: "b", h: 48 }
        n0 --> n3
        n0 --> n1
        n1 --> n2
        n8 --> n4
        n2 --> n5
        n5 --> n8
        n10 --> n6
        n9 --> n7
        n7 --> n0
        n3 --> n1
        n4 --> n10
    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 n9 trigger
    class n4,n5,n10 ai
    class n0 decision
    class n2,n3,n6 database
    class n7,n8 api
    classDef customIcon fill:none,stroke:none
    class n1,n7,n8,n9 customIcon

Why This Matters: Turning Trends Into Usable Ideas

YouTube “trend research” sounds lightweight until you actually do it. You search a keyword, open trending videos, and start collecting notes. Then the real work begins: deciding what’s worth copying (structure, not content), pulling details into a doc, and trying to write a better title without losing the original context. After a week, your ideas live in three places, duplicates sneak in, and you can’t remember why a link was saved. The worst part is the mental load. Your brain is doing admin when it should be spotting patterns.

It adds up fast. Here’s where it usually breaks down.

You end up re-checking the same channels because there’s no clean record of what you already reviewed.
Copy-pasting titles and URLs sounds quick, but it’s easy to mislabel rows or miss key context like thumbnail angle or narrative hook.
Transcripts are useful, yet pulling them manually is tedious, so most people skip them and settle for shallow ideas.
Duplicates slip into the backlog, which means your “idea list” grows while your confidence in it drops.

What You’ll Build: YouTube Trend Research to Sheet-Ready Concepts

This workflow turns a simple keyword into a short list of usable content angles, stored neatly in Google Sheets. It starts with a form submission (you type a topic like “AI automation”). n8n sends that keyword to an Apify-powered scrape via HTTP Request to pull trending YouTube videos and metadata. From there, a conditional check filters the results and looks up your existing sheet rows to avoid repeats. When a video passes the gate, it gets appended to your sheet, then AI steps in: it analyzes the thumbnail for what’s working visually, retrieves the transcript, generates a stronger “inspired-by” title, and finally produces an outline draft you can actually hand to a writer or use yourself. The sheet rows are updated with those AI outputs so you’re not hunting through chat logs later.

The workflow starts when you submit a keyword in the form. It then collects candidate videos, checks your Google Sheet for duplicates, and appends fresh rows. After that, OpenAI analyzes the thumbnail and transcript, then writes a title and outline before updating the same row so everything stays connected.

What You’re Building

What Gets Automated

What You’ll Achieve

Submitting one keyword through a simple n8n form to kick off research.
Scraping trending YouTube video listings via Apify using HTTP Request nodes.
Checking Google Sheets to catch duplicate video entries before they pollute your backlog.
Running thumbnail + transcript analysis with OpenAI, then writing titles and outlines automatically.

Turn a 45-minute research pass into about 10 minutes of real decision-making.
Keep one searchable “source of truth” sheet your whole team can use.
Get more consistent hooks because thumbnail and transcript signals are captured, not guessed.
Reduce duplicate ideas so weekly planning meetings feel easier.
Move faster from “interesting trend” to “ready-to-brief outline.”

Expected Results

Say you research one keyword per day and shortlist 10 videos. Manually, you might spend about 3 minutes per video copying details into a sheet, then another 5 minutes skimming and drafting a better title and quick outline, so roughly 80 minutes total. With this workflow, the “human time” is closer to 5 minutes to submit the keyword and skim the sheet after it runs; the rest is automated processing time. That’s about an hour back each day you do research.

Before You Start

n8n instance (try n8n Cloud free)
Self-hosting option if you prefer (Hostinger works well)
Google Sheets for storing research and AI outputs.
Apify to scrape video listings and transcripts.
OpenAI API Key (get it from your OpenAI API settings page)

Skill level: Beginner. You’ll paste API keys, connect Google Sheets OAuth, and change a Sheet ID.

Want someone to build this for you? Talk to an automation expert (free 15-minute consultation).

Step by Step

A keyword submission kicks things off. You type “Keyword or Topic” into the built-in n8n form. That single input becomes the seed for the whole research run.

YouTube trend data gets pulled in. An HTTP Request node calls Apify to fetch trending video listings related to your keyword. The workflow then uses a simple conditional gate to decide which results are worth processing (so you’re not filling your sheet with junk).

Duplicates are handled before they waste your time. n8n checks your Google Sheet for existing rows, merges the “new” and “existing” streams, and only appends what’s actually new. Clean backlog, less confusion later.

AI turns raw videos into usable briefs. OpenAI analyzes the thumbnail (so you understand the visual hook), pulls the transcript, generates a better title, then creates an outline draft. Finally, n8n updates the same Google Sheet row, keeping every insight tied to the exact video.

You can easily modify the filtering rules to be stricter or looser based on your niche. See the full implementation guide below for customization options.

Step-by-Step Implementation Guide

Step 1: Configure the Form Submission Trigger

Set up the form that collects a topic keyword and starts the workflow.

Add and open Form Submission Trigger.
Set Form Title to YouTube Topic Research.
Add a required form field with Field Label set to Keyword or Topic.
Set Form Description to Enter a keyword or topic below, and I'll find trending videos related to that topic..

You can keep Flowpast Branding as a visual reference; it does not affect execution.

Step 2: Connect the Video Data Source

Pull trending YouTube listings from Apify using the submitted keyword.

Add and open Fetch Video Listings.
Set URL to https://api.apify.com/v2/acts/h7sDV53CddomktSi5/run-sync-get-dataset-items and Method to POST.
Set Specify Body to json and paste the full JSON Body value as provided, including the expression {{ $json['Keyword or Topic'] }} in searchQueries.
In Header Parameters, set Accept to application/json and Authorization to Bearer [CONFIGURE_YOUR_TOKEN] with your Apify token.

⚠️ Common Pitfall: Leaving the Authorization header as Bearer [CONFIGURE_YOUR_TOKEN] will cause 401 errors. Replace it with your real Apify token.

Step 3: Filter and De-duplicate Results

Filter videos by view count and prevent duplicates before writing to Google Sheets.

Add and configure Conditional Gate with two conditions: Left Value ={{ $json.viewCount }} Operation gt Right Value 1000, and Left Value ={{ $json.viewCount }} Operation gt Right Value ={{ $json.numberOfSubscribers }}.
Add Check Existing Rows and set Document to your spreadsheet and Sheet Name to your target tab (replace [YOUR_ID] values).
In Check Existing Rows, add a filter with Lookup Column set to id and Lookup Value set to ={{ $json.id }}.
Add Combine Streams and set Mode to combine, Join Mode to keepNonMatches, Output Data From to input2, and Fields To Match to id.
Ensure the execution flow matches: Conditional Gate outputs to both Check Existing Rows and Combine Streams in parallel.

Credential Required: Connect your Google Sheets credentials in Check Existing Rows.

Step 4: Append New Records to Google Sheets

Store the filtered video metadata in your sheet so downstream AI steps can enrich it.

Add Append Sheet Records and set Operation to append.
Set Document and Sheet Name to your target sheet (replace [YOUR_ID] values).
Map the columns exactly as configured, including: id ={{ $json.id }}, url ={{ $('Conditional Gate').item.json.url }}, title ={{ $('Conditional Gate').item.json.title }}, thumbnailUrl ={{ $('Conditional Gate').item.json.thumbnailUrl }}, and the other fields shown in the node.

Credential Required: Connect your Google Sheets credentials in Append Sheet Records.

Step 5: Set Up AI Enrichment (Thumbnail, Title, and Outline)

Analyze thumbnails, fetch transcripts, and generate improved titles and outlines using OpenAI.

Add Thumbnail Insight with Resource set to image, Operation to analyze, and Image URLs set to ={{ $('Append Sheet Records').item.json.thumbnailUrl }}.
Set Model in Thumbnail Insight to gpt-4o-mini and keep the provided prompt text as-is.
Add Retrieve Transcript and set URL to https://api.apify.com/v2/acts/1s7eXiaukVuOr4Ueg/run-sync-get-dataset-items with Method POST. Keep the provided JSON Body and set urls to {{ $('Append Sheet Records').item.json.url }}.
In Retrieve Transcript, set the Authorization header to Bearer [CONFIGURE_YOUR_TOKEN] using your Apify token.
Add Generate Video Title with Model set to gpt-4.1-mini, JSON Output enabled, and keep the provided message content that references {{ $('Append Sheet Records').item.json.title }}, {{ $('Thumbnail Insight').item.json.choices[0].message.content }}, and {{ $('Retrieve Transcript').item.json.captions }}.
Add Create Outline Draft with Model set to gpt-4.1 and keep the provided system prompt and transcript input {{ $('Retrieve Transcript').item.json.captions }}.

Credential Required: Connect your OpenAI credentials in Thumbnail Insight, Generate Video Title, and Create Outline Draft.

Step 6: Update the Sheet With AI Outputs

Write the generated title, thumbnail text, transcript, and outline back to the original row.

Add Modify Sheet Rows and set Operation to update.
Set Document and Sheet Name to your target sheet (replace [YOUR_ID] values).
Map id to ={{ $('Append Sheet Records').item.json.id }} and set the AI fields: newTitle to ={{ $('Generate Video Title').item.json.choices[0].message.content.newTitle }}, thumbnailText to ={{ $('Generate Video Title').item.json.choices[0].message.content.thumbnailText }}, newOutline to ={{ $json.choices[0].message.content }}, videoTranscript to ={{ $('Retrieve Transcript').item.json.captions }}, and thumbnailDescription to ={{ $('Thumbnail Insight').item.json.choices[0].message.content }}.

Credential Required: Connect your Google Sheets credentials in Modify Sheet Rows.

Step 7: Test and Activate Your Workflow

Run a full test to ensure data flows through the parallel branch and AI enrichment steps.

Click Execute Workflow and submit the form in Form Submission Trigger with a sample keyword.
Confirm that Conditional Gate filters results and that it outputs to both Check Existing Rows and Combine Streams in parallel.
Verify a new row is appended by Append Sheet Records and then enriched by Thumbnail Insight, Retrieve Transcript, Generate Video Title, and Create Outline Draft.
Check the final row update from Modify Sheet Rows for populated fields: newTitle, thumbnailText, newOutline, videoTranscript, and thumbnailDescription.
When satisfied, toggle the workflow to Active to accept live form submissions.

🔒

Unlock Full Step-by-Step Guide

Get the complete implementation guide + downloadable template

Troubleshooting Tips

Google Sheets credentials can expire or need specific permissions. If things break, check the Google Sheets OAuth connection in n8n’s Credentials list first.
Apify requests can fail if the API token isn’t added to both HTTP Request nodes (the Authorization header is easy to miss). Re-paste the token and re-run with a single keyword to confirm.
Default prompts in AI nodes are generic. Add your brand voice early or you’ll be editing outputs forever.

Quick Answers

What’s the setup time for this YouTube Sheets automation automation?

About 20 minutes if you already have your accounts.

Is coding required for this YouTube Sheets automation?

No. You’ll connect credentials, paste API keys, and update a Google Sheet ID.

Is n8n free to use for this YouTube Sheets automation workflow?

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 OpenAI API usage costs (often just cents for small batches) and whatever Apify charges for your runs.

Where can I host n8n to run this automation?

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.

Can I modify this YouTube Sheets automation workflow for different use cases?

Yes, and you should. Most people tweak the filtering in the Conditional Gate so the sheet only gets videos that match their niche, then adjust the prompts in Thumbnail Insight, Generate Video Title, and Create Outline Draft to match brand voice. You can also swap the Google Sheets steps to write into a different tab for each content pillar. If you don’t want transcript-based writing, skip the transcript step and use thumbnail + metadata only.

Why is my Google Sheets connection failing in this workflow?

Usually it’s OAuth permissions or the wrong Google account connected. Reconnect the Google Sheets credential in n8n, then confirm the account can access the target Sheet in Drive. Also double-check the documentId used in the “check rows” and “update rows” steps, because a single wrong ID looks like a permissions issue. If it fails only sometimes, you may be hitting Google API quotas during larger runs.

What volume can this YouTube Sheets automation workflow process?

On n8n Cloud you’re mainly limited by plan executions and how many videos you pull per run; self-hosting removes execution caps, but your server still needs to handle the load. Practically, most teams run this a few times a week per niche keyword and keep the batch size modest so OpenAI and transcript pulls don’t bottleneck.

Is this YouTube Sheets automation automation better than using Zapier or Make?

Often, yes, because this workflow has branching, deduping, and multi-step AI processing that gets awkward (and expensive) in simpler tools. n8n also makes it easier to mix “research scraping” with “update the same row later” behavior, which is the whole point of keeping a clean backlog. Zapier and Make are totally fine for lightweight two-app zaps, but this isn’t that. If your team wants to productionize this and keep costs predictable, n8n is usually the calmer choice. Talk to an automation expert if you want help picking the right stack.

You do the thinking. The workflow does the collecting, deduping, and drafting. Once it’s running, trend research stops feeling like a chore.

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.

Lisa Granqvist

Workflow Automation Expert

Expert in workflow automation and no-code tools.

{
"id": null,
"name": "Automated Video Research Workflow",
"versionId": null,
"meta": {
"instanceId": "b17e9091a53c57a333f70c4cf67b284915bbea6529afaa074a7f15fd2e5a7fc7",
"templateId": null,
"templateCredsSetupCompleted": null
},
"nodes": [
{
"id": "flowpast-topbar-8023",
"name": "Flowpast Branding",
"type": "n8n-nodes-base.stickyNote",
"position": [
0,
20
],
"parameters": {
"color": 7,
"width": 780,
"height": 80,
"content": "## Flowpast.com | Automation Workflow Library\n**\ud83d\udcd6 Full tutorial & setup guide:** flowpast.com"
},
"typeVersion": 1
},
{
"id": "b6553d58-da4d-4aba-8660-1b777018feb7",
"name": "Form Submission Trigger",
"type": "n8n-nodes-base.formTrigger",
"position": [
0,
170
],
"webhookId": "29de0389-1bc3-46b2-8125-f2cfc5bd0d29",
"parameters": {
"options": [],
"formTitle": "YouTube Topic Research",
"formFields": {
"values": [
{
"fieldLabel": "Keyword or Topic",
"requiredField": true
}
]
},
"formDescription": "Enter a keyword or topic below, and I'll find trending videos related to that topic. "
},
"typeVersion": 2.2
},
{
"id": "7a835dcc-5b53-4a53-b95a-540c59d0a0de",
"name": "Fetch Video Listings",
"type": "n8n-nodes-base.httpRequest",
"position": [
220,
130
],
"parameters": {
"url": "https://api.apify.com/v2/acts/h7sDV53CddomktSi5/run-sync-get-dataset-items",
"method": "POST",
"options": {
"redirect": {
"redirect": []
}
},
"jsonBody": "={\n  \"dateFilter\": \"month\",\n  \"downloadSubtitles\": false,\n  \"hasCC\": false,\n  \"hasLocation\": false,\n  \"hasSubtitles\": false,\n  \"is360\": false,\n  \"is3D\": false,\n  \"is4K\": false,\n  \"isBought\": false,\n  \"isHD\": false,\n  \"isHDR\": false,\n  \"isLive\": false,\n  \"isVR180\": false,\n  \"lengthFilter\": \"between420\",\n  \"maxResultStreams\": 0,\n  \"maxResults\": 100,\n  \"maxResultsShorts\": 0,\n  \"preferAutoGeneratedSubtitles\": false,\n  \"saveSubsToKVS\": false,\n  \"scrapeLastNDays\": 60,\n  \"searchQueries\": [\n    \"{{ $json['Keyword or Topic'] }}\"\n  ],\n  \"sortVideosBy\": \"NEWEST\",\n  \"sortingOrder\": \"date\",\n  \"videoType\": \"video\"\n}",
"sendBody": true,
"sendHeaders": true,
"specifyBody": "json",
"headerParameters": {
"parameters": [
{
"name": "Accept",
"value": "application/json"
},
{
"name": "Authorization",
"value": "Bearer [CONFIGURE_YOUR_TOKEN]"
}
]
}
},
"typeVersion": 4.2
},
{
"id": "d0605ee4-1304-4fe7-b0da-55d46bca2428",
"name": "Conditional Gate",
"type": "n8n-nodes-base.if",
"position": [
450,
180
],
"parameters": {
"options": [],
"conditions": {
"options": {
"version": 2,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "a179d690-a6da-41ef-9ca4-7346864f7233",
"operator": {
"type": "number",
"operation": "gt"
},
"leftValue": "={{ $json.viewCount }}",
"rightValue": 1000
},
{
"id": "b66e2013-6fc7-414d-bf7b-5c6c7e23bcae",
"operator": {
"type": "number",
"operation": "gt"
},
"leftValue": "={{ $json.viewCount }}",
"rightValue": "={{ $json.numberOfSubscribers }}"
}
]
}
},
"typeVersion": 2.2
},
{
"id": "681b01b1-4bd5-4782-969c-286ab571db14",
"name": "Check Existing Rows",
"type": "n8n-nodes-base.googleSheets",
"position": [
680,
120
],
"parameters": {
"options": [],
"filtersUI": {
"values": [
{
"lookupValue": "={{ $json.id }}",
"lookupColumn": "id"
}
]
},
"sheetName": {
"__rl": true,
"mode": "list",
"value": "[YOUR_ID]",
"cachedResultName": "Step 1"
},
"documentId": {
"__rl": true,
"mode": "list",
"value": "[YOUR_ID]",
"cachedResultName": "YouTube Videos"
}
},
"executeOnce": false,
"typeVersion": 4.5,
"alwaysOutputData": false
},
{
"id": "a8006ffd-f3cd-48e9-b62c-89ae9cd4b556",
"name": "Combine Streams",
"type": "n8n-nodes-base.merge",
"position": [
615,
390
],
"parameters": {
"mode": "combine",
"options": [],
"joinMode": "keepNonMatches",
"outputDataFrom": "input2",
"fieldsToMatchString": "id"
},
"typeVersion": 3.1
},
{
"id": "3980893b-c2fb-45e4-911e-2e0a10f5aeb0",
"name": "Append Sheet Records",
"type": "n8n-nodes-base.googleSheets",
"position": [
380,
330
],
"parameters": {
"columns": {
"value": {
"id": "={{ $json.id }}",
"url": "={{ $('Conditional Gate').item.json.url }}",
"input": "={{ $('Conditional Gate').item.json.input }}",
"likes": "={{ $('Conditional Gate').item.json.likes }}",
"title": "={{ $('Conditional Gate').item.json.title }}",
"duration": "={{ $('Conditional Gate').item.json.duration }}",
"fromYTUrl": "={{ $('Conditional Gate').item.json.fromYTUrl }}",
"viewCount": "={{ $('Conditional Gate').item.json.viewCount }}",
"channelUrl": "={{ $('Conditional Gate').item.json.channelUrl }}",
"channelName": "={{ $('Conditional Gate').item.json.channelName }}",
"thumbnailUrl": "={{ $('Conditional Gate').item.json.thumbnailUrl }}",
"numberOfSubscribers": "={{ $('Conditional Gate').item.json.numberOfSubscribers }}"
},
"schema": [
{
"id": "input",
"type": "string",
"display": true,
"required": false,
"displayName": "input",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "id",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "id",
"defaultMatch": true,
"canBeUsedToMatch": true
},
{
"id": "title",
"type": "string",
"display": true,
"required": false,
"displayName": "title",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "url",
"type": "string",
"display": true,
"required": false,
"displayName": "url",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "fromYTUrl",
"type": "string",
"display": true,
"required": false,
"displayName": "fromYTUrl",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "thumbnailUrl",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "thumbnailUrl",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "channelName",
"type": "string",
"display": true,
"required": false,
"displayName": "channelName",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "channelUrl",
"type": "string",
"display": true,
"required": false,
"displayName": "channelUrl",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "duration",
"type": "string",
"display": true,
"required": false,
"displayName": "duration",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "likes",
"type": "string",
"display": true,
"required": false,
"displayName": "likes",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "numberOfSubscribers",
"type": "string",
"display": true,
"required": false,
"displayName": "numberOfSubscribers",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "viewCount",
"type": "string",
"display": true,
"required": false,
"displayName": "viewCount",
"defaultMatch": false,
"canBeUsedToMatch": true
}
],
"mappingMode": "defineBelow",
"matchingColumns": [
"id"
],
"attemptToConvertTypes": false,
"convertFieldsToString": false
},
"options": [],
"operation": "append",
"sheetName": {
"__rl": true,
"mode": "list",
"value": "[YOUR_ID]",
"cachedResultName": "Step 1"
},
"documentId": {
"__rl": true,
"mode": "list",
"value": "[YOUR_ID]",
"cachedResultName": "YouTube Videos"
}
},
"typeVersion": 4.5
},
{
"id": "8c200f72-d742-4117-9291-57c52ba3b278",
"name": "Thumbnail Insight",
"type": "@n8n/n8n-nodes-langchain.openAi",
"position": [
235,
375
],
"parameters": {
"text": "=# Overview  \nYou are an AI agent responsible for analyzing a YouTube thumbnail via a provided URL and generating a single, well-written **natural language description** that captures the visual style, layout, and tone of the thumbnail. This description will be used as part of an image generation prompt to recreate a similarly styled thumbnail.\n\n## Context  \n- The agent uses OpenAI\u2019s image understanding capabilities to visually analyze YouTube thumbnails.  \n- The goal is to create a **descriptive text output** that reflects the design, mood, and layout of the thumbnail \u2014 not to copy the content directly.  \n- The output should be a standalone sentence or paragraph in natural language, ready to be embedded in a larger prompt.\n\n## Instructions  \n1. Retrieve and analyze the thumbnail image from the given YouTube URL.  \n2. Identify and describe the following elements:\n   - Overall layout and composition  \n   - Character or subject placement (if applicable)  \n   - Background type and visual treatment  \n   - Font and text style, including content if legible  \n   - Dominant color palette and mood  \n3. Compose a fluent, single-string natural language description of the thumbnail.  \n4. The output should read like part of a prompt, e.g., \"An energetic YouTube thumbnail showing...\"  \n5. Do not include any structured formatting (like JSON, lists, or metadata).  \n\n## Tools  \n- OpenAI Image Understanding Node  \n\n## Examples  \n- **Input:**  \n  `https://i.ytimg.com/vi/HpkZU34fqUM/maxresdefault.jpg`  \n- **Output:**  \n  A high-energy YouTube thumbnail featuring a surprised man on the right side, with a bold red radial gradient background. Large comic-style yellow text appears on the left, creating a dramatic and urgent visual tone.\n\n- **Input:**  \n  `https://i.ytimg.com/vi/abc123xyz/default.jpg`  \n- **Output:**  \n  A clean, professional thumbnail showing a laptop with a blurred tech-themed background. Soft blue and gray tones dominate the scene, with sleek sans-serif text centered above the device.\n\n## SOP (Standard Operating Procedure)  \n1. Validate the provided YouTube thumbnail URL.  \n2. Retrieve the image and perform visual analysis using image capabilities.  \n3. Extract and synthesize details about layout, colors, subjects, and visual emphasis.  \n4. Write a **natural language description** that feels prompt-ready, descriptive, and cohesive.  \n5. Return only the final descriptive sentence or paragraph \u2014 no metadata, formatting, or JSON.\n\n## Final Notes  \n- Do not refer to brand names, creators, or exact text unless it's generic and descriptive.  \n- Focus on tone, layout, and composition to support style transfer, not replication.  \n- The description should serve as a high-quality visual summary usable in generative models.\n---",
"modelId": {
"__rl": true,
"mode": "list",
"value": "gpt-4o-mini",
"cachedResultName": "GPT-4O-MINI"
},
"options": {
"detail": "high"
},
"resource": "image",
"simplify": false,
"imageUrls": "={{ $('Append Sheet Records').item.json.thumbnailUrl }}",
"operation": "analyze"
},
"typeVersion": 1.8
},
{
"id": "8ee684c9-d495-4bf2-9e1a-59c0f07ecadd",
"name": "Retrieve Transcript",
"type": "n8n-nodes-base.httpRequest",
"position": [
10,
315
],
"parameters": {
"url": "https://api.apify.com/v2/acts/1s7eXiaukVuOr4Ueg/run-sync-get-dataset-items",
"method": "POST",
"options": {
"redirect": {
"redirect": []
}
},
"jsonBody": "={\n  \"channelHandleBoolean\": true,\n  \"channelIDBoolean\": false,\n  \"channelNameBoolean\": true,\n  \"commentsBoolean\": false,\n  \"datePublishedBoolean\": false,\n  \"dateTextBoolean\": false,\n  \"descriptionBoolean\": false,\n  \"keywordsBoolean\": true,\n  \"likesBoolean\": false,\n  \"maxRetries\": 8,\n  \"outputFormat\": \"singleStringText\",\n  \"proxyOptions\": {\n    \"useApifyProxy\": true,\n    \"apifyProxyGroups\": []\n  },\n  \"relativeDateTextBoolean\": false,\n  \"subscriberCountBoolean\": false,\n  \"thumbnailBoolean\": false,\n  \"uploadDateBoolean\": false,\n  \"urls\": [\n    \"{{ $('Append Sheet Records').item.json.url }}\"\n  ],\n  \"viewCountBoolean\": false\n}",
"sendBody": true,
"sendHeaders": true,
"specifyBody": "json",
"headerParameters": {
"parameters": [
{
"name": "Accept",
"value": "application/json"
},
{
"name": "Authorization",
"value": "Bearer [CONFIGURE_YOUR_TOKEN]"
}
]
}
},
"typeVersion": 4.2
},
{
"id": "ab8658bf-c5f1-402b-99c6-0d1b6d30f63e",
"name": "Generate Video Title",
"type": "@n8n/n8n-nodes-langchain.openAi",
"position": [
25,
580
],
"parameters": {
"modelId": {
"__rl": true,
"mode": "list",
"value": "gpt-4.1-mini",
"cachedResultName": "GPT-4.1-MINI"
},
"options": [],
"messages": {
"values": [
{
"content": "=Video Title: {{ $('Append Sheet Records').item.json.title }}\nThumbnail Description: {{ $('Thumbnail Insight').item.json.choices[0].message.content }}\nVideo Transcript: {{ $('Retrieve Transcript').item.json.captions }}"
},
{
"role": "system",
"content": "=# Overview  \nYou are an AI agent responsible for generating an optimized YouTube video title and corresponding thumbnail text based on an original title, visual thumbnail analysis, and video transcript. Your goal is to retain the original message while improving clarity, engagement, and visual storytelling.\n\n## Context  \n- You will receive:\n  - The original video title  \n  - A natural language description of the thumbnail image  \n  - The full video transcript  \n- Your output should be a single JSON object that includes:\n  - A revised, SEO-optimized video title  \n  - Concise thumbnail text (3\u20135 words) that complements the revised title and aligns with the thumbnail\u2019s visual tone.\n\n## Instructions  \n1. Read and analyze the original video title for its main topic and keywords.  \n2. Use the thumbnail description and video transcript to better understand the visual and content themes.  \n3. Generate a new title that:\n   - Maintains the original intent and main keywords  \n   - Improves structure, clarity, or emotional appeal  \n   - Stays under 70 characters  \n4. Create 3\u20135 words of thumbnail text that:\n   - Adds insight, urgency, or intrigue to support the title  \n   - Aligns with the visual style of the thumbnail  \n   - Feels natural when paired with the title  \n\n5. Output a single JSON object with both the revised title and thumbnail text in the following format:  \n   ```json\n   {\n     \"newTitle\": \"Improved YouTube video title\",\n     \"thumbnailText\": \"3\u20135 word thumbnail text\"\n   }\n   ```\n\n## Tools  \n- Original Title: `{{ $('Append Sheet Records').item.json.title }}`  \n- Thumbnail Description: `{{ $('Thumbnail Insight').item.json.choices[0].message.content }}`  \n- Video Transcript: `{{ $('Retrieve Transcript').item.json.captions }}`  \n\n## Examples  \n**Input:**  \n- Title: `\"He Built an AI Business With Just $100\"`  \n- Thumbnail Description: `\"A thumbnail showing a confident man pointing at a laptop, with large text reading 'From $100 to CEO'. The background features glowing tech icons on a dark gradient backdrop.\"`  \n- Transcript: *Describes how the subject bootstrapped a business using AI tools and minimal funding.*\n\n**Output:**  \n```json\n{\n  \"newTitle\": \"How He Launched an AI Startup with $100\",\n  \"thumbnailText\": \"AI Startup for $100\"\n}\n```\n\n**Input:**  \n- Title: `\"Top 10 ChatGPT Hacks You Didn't Know\"`  \n- Thumbnail Description: `\"A sleek modern thumbnail with neon text that says 'ChatGPT Tricks', showing a split screen of a person thinking and a glowing terminal interface.\"`  \n- Transcript: *Lists lesser-known prompts and features to boost productivity.*\n\n**Output:**  \n```json\n{\n  \"newTitle\": \"10 ChatGPT Hacks to Boost Productivity\",\n  \"thumbnailText\": \"Hidden GPT Features\"\n}\n```\n\n## SOP (Standard Operating Procedure)  \n1. Parse the input values: original title, thumbnail description, and transcript.  \n2. Identify key themes and keywords from the title.  \n3. Use visual and transcript context to improve the relevance and appeal of the new title.  \n4. Draft 1\u20132 thumbnail text options based on visual cues and the revised title.  \n5. Select the most compelling option.  \n6. Return the output as a clean JSON object with both fields.\n\n## Final Notes  \n- Do not include brand names or identifiable individuals unless they are generic and essential.  \n- Avoid vague adjectives and hype-driven phrasing.  \n- Keep the output concise, natural, and clear \u2014 ready for immediate use in automation or upload.\n---"
}
]
},
"simplify": false,
"jsonOutput": true
},
"typeVersion": 1.8
},
{
"id": "05e6cf15-0652-4765-b4d7-90a80ed797b9",
"name": "Create Outline Draft",
"type": "@n8n/n8n-nodes-langchain.openAi",
"position": [
170,
510
],
"parameters": {
"modelId": {
"__rl": true,
"mode": "list",
"value": "gpt-4.1",
"cachedResultName": "GPT-4.1"
},
"options": [],
"messages": {
"values": [
{
"role": "system",
"content": "=# Overview  \nYou are an AI agent responsible for analyzing high-performing YouTube video transcripts and generating improved, original video outlines with a unique perspective.  \n\n## Context  \n- The agent receives the transcript of a successful YouTube video from another creator.  \n- The goal is not to copy, but to use the structure and content as a benchmark to craft a new outline that offers a distinct angle or interpretation of the topic.  \n- The resulting outline should maintain the engaging qualities of the original while providing fresh value to the target audience.  \n\n## Instructions  \n1. Analyze the input transcript to understand the topic, flow, structure, and elements that likely contributed to its performance.  \n2. Identify opportunities to reinterpret, reframe, or expand on the topic in a unique way.  \n3. Develop a new outline that:\n   - Retains the core appeal of the original video.  \n   - Presents a different perspective, argument, or theme.  \n   - Enhances clarity, relatability, and retention where possible.  \n4. Structure the new outline into standard YouTube sections (Hook, Introduction, Main Points, Call to Action, etc.).  \n5. Ensure the tone and content are original and distinct while still appealing to a similar audience.  \n\n## Tools  \n- None (analysis and outline generation only)  \n\n## Examples  \n- Input:  \n {{ $('Retrieve Transcript').item.json.captions }}\n\n- Output:  \n  - Hook: Challenge a commonly held belief related to the topic.  \n  - Introduction: Present your own experience or angle on the issue.  \n  - Section 1: Explore the topic using a new metaphor or real-world example.  \n  - Section 2: Address a subtopic the original did not cover.  \n  - Section 3: Offer actionable advice or a unique conclusion.  \n  - Call to Action: Encourage viewers to comment with their own experiences or thoughts.  \n\n## SOP (Standard Operating Procedure)  \n1. Review the transcript to understand key takeaways, pacing, and style.  \n2. Extract the main topic and how the original creator approached it.  \n3. Brainstorm unique takes, new angles, or opposing views that can form the basis of a fresh outline.  \n4. Draft an outline that follows a proven structure but deviates meaningfully in substance or perspective.  \n5. Return the new outline in a clean, sectioned bullet-point format ready for video scripting.  \n\n## Final Notes  \n- The goal is to differentiate while building on what worked.  \n- Avoid mirroring phrases or points from the original\u2014reframe and rephrase.  \n- The final outline should feel original, relevant, and optimized for YouTube engagement.  \n---"
},
{
"content": "=Video Transcript: {{ $('Retrieve Transcript').item.json.captions }}"
}
]
},
"simplify": false
},
"typeVersion": 1.8
},
{
"id": "7b7ecf58-980e-416c-b20c-698d9dd2cb3d",
"name": "Modify Sheet Rows",
"type": "n8n-nodes-base.googleSheets",
"position": [
445,
570
],
"parameters": {
"columns": {
"value": {
"id": "={{ $('Append Sheet Records').item.json.id }}",
"newTitle": "={{ $('Generate Video Title').item.json.choices[0].message.content.newTitle }}",
"newOutline": "={{ $json.choices[0].message.content }}",
"thumbnailText": "={{ $('Generate Video Title').item.json.choices[0].message.content.thumbnailText }}",
"videoTranscript": "={{ $('Retrieve Transcript').item.json.captions }}",
"thumbnailDescription": "={{ $('Thumbnail Insight').item.json.choices[0].message.content }}"
},
"schema": [
{
"id": "input",
"type": "string",
"display": true,
"removed": true,
"required": false,
"displayName": "input",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "id",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "id",
"defaultMatch": true,
"canBeUsedToMatch": true
},
{
"id": "title",
"type": "string",
"display": true,
"removed": true,
"required": false,
"displayName": "title",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "url",
"type": "string",
"display": true,
"removed": true,
"required": false,
"displayName": "url",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "fromYTUrl",
"type": "string",
"display": true,
"removed": true,
"required": false,
"displayName": "fromYTUrl",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "thumbnailUrl",
"type": "string",
"display": true,
"removed": true,
"required": false,
"displayName": "thumbnailUrl",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "channelName",
"type": "string",
"display": true,
"removed": true,
"required": false,
"displayName": "channelName",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "channelUrl",
"type": "string",
"display": true,
"removed": true,
"required": false,
"displayName": "channelUrl",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "duration",
"type": "string",
"display": true,
"removed": true,
"required": false,
"displayName": "duration",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "likes",
"type": "string",
"display": true,
"removed": true,
"required": false,
"displayName": "likes",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "numberOfSubscribers",
"type": "string",
"display": true,
"removed": true,
"required": false,
"displayName": "numberOfSubscribers",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "viewCount",
"type": "string",
"display": true,
"removed": true,
"required": false,
"displayName": "viewCount",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "videoTranscript",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "videoTranscript",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "thumbnailDescription",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "thumbnailDescription",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "thumbnailText",
"type": "string",
"display": true,
"required": false,
"displayName": "thumbnailText",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "newTitle",
"type": "string",
"display": true,
"required": false,
"displayName": "newTitle",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "newOutline",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "newOutline",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "row_number",
"type": "string",
"display": true,
"removed": true,
"readOnly": true,
"required": false,
"displayName": "row_number",
"defaultMatch": false,
"canBeUsedToMatch": true
}
],
"mappingMode": "defineBelow",
"matchingColumns": [
"id"
],
"attemptToConvertTypes": false,
"convertFieldsToString": false
},
"options": [],
"operation": "update",
"sheetName": {
"__rl": true,
"mode": "list",
"value": "[YOUR_ID]",
"cachedResultName": "Step 1"
},
"documentId": {
"__rl": true,
"mode": "list",
"value": "[YOUR_ID]",
"cachedResultName": "YouTube Videos"
}
},
"typeVersion": 4.5
}
],
"pinData": [],
"connections": {
"Conditional Gate": {
"main": [
[
{
"node": "Check Existing Rows",
"type": "main",
"index": 0
},
{
"node": "Combine Streams",
"type": "main",
"index": 1
}
]
]
},
"Combine Streams": {
"main": [
[
{
"node": "Append Sheet Records",
"type": "main",
"index": 0
}
]
]
},
"Retrieve Transcript": {
"main": [
[
{
"node": "Generate Video Title",
"type": "main",
"index": 0
}
]
]
},
"Append Sheet Records": {
"main": [
[
{
"node": "Thumbnail Insight",
"type": "main",
"index": 0
}
]
]
},
"Thumbnail Insight": {
"main": [
[
{
"node": "Retrieve Transcript",
"type": "main",
"index": 0
}
]
]
},
"Create Outline Draft": {
"main": [
[
{
"node": "Modify Sheet Rows",
"type": "main",
"index": 0
}
]
]
},
"Form Submission Trigger": {
"main": [
[
{
"node": "Fetch Video Listings",
"type": "main",
"index": 0
}
]
]
},
"Fetch Video Listings": {
"main": [
[
{
"node": "Conditional Gate",
"type": "main",
"index": 0
}
]
]
},
"Check Existing Rows": {
"main": [
[
{
"node": "Combine Streams",
"type": "main",
"index": 0
}
]
]
},
"Generate Video Title": {
"main": [
[
{
"node": "Create Outline Draft",
"type": "main",
"index": 0
}
]
]
}
}
}