TikTok to Google Drive, trend videos ready to review
You find a trend, bookmark it, forget why it mattered, then scramble the day you need to post. Meanwhile your “ideas” live across likes, notes, DMs, and half-finished docs.
This TikTok Drive automation hits social media managers first, but marketers building content engines feel it too. A busy creator trying to post consistently? Same pain, just louder. The outcome is simple: a steady stream of fresh, review-ready short videos organized in Google Drive.
You will see how this n8n workflow takes trend research, turns it into AI video prompts, generates new vertical videos, and files everything neatly for approval and posting.
How This Automation Works
The full n8n workflow, from trigger to final output:
n8n Workflow Template: TikTok to Google Drive, trend videos ready to review
flowchart LR
subgraph sg0["Manual Execution Start Flow"]
direction LR
n0@{ icon: "mdi:play-circle", form: "rounded", label: "Manual Execution Start", 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/httprequest.dark.svg' width='40' height='40' /></div><br/>Start Scrape Run"]
n2@{ icon: "mdi:cog", form: "rounded", label: "Delay Execution", pos: "b", h: 48 }
n3["<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/>Fetch Scrape Results"]
n4@{ icon: "mdi:database", form: "rounded", label: "Update Raw Sheet", pos: "b", h: 48 }
n5@{ icon: "mdi:cog", form: "rounded", label: "Record Limit", pos: "b", h: 48 }
n6@{ icon: "mdi:robot", form: "rounded", label: "AI Prompt Builder", pos: "b", h: 48 }
n7@{ icon: "mdi:brain", form: "rounded", label: "OpenRouter Chat Engine", pos: "b", h: 48 }
n8@{ icon: "mdi:database", form: "rounded", label: "Update Prompt Sheet", pos: "b", h: 48 }
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/httprequest.dark.svg' width='40' height='40' /></div><br/>Fal Video Submission"]
n10@{ icon: "mdi:cog", form: "rounded", label: "Generation Pause", pos: "b", h: 48 }
n11["<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/>Retrieve Render Output"]
n12@{ icon: "mdi:cog", form: "rounded", label: "Drive File Upload", pos: "b", h: 48 }
n2 --> n3
n5 --> n6
n10 --> n11
n6 --> n8
n9 --> n10
n1 --> n2
n3 --> n4
n11 --> n12
n7 -.-> n6
n4 --> n5
n8 --> n9
n0 --> n1
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 n0 trigger
class n6 ai
class n7 aiModel
class n4,n8 database
class n1,n3,n9,n11 api
classDef customIcon fill:none,stroke:none
class n1,n3,n9,n11 customIcon
The Problem: Trend Research Doesn’t Turn Into Postable Assets
Trend research is easy. Turning it into something your brand can actually publish is the grind. You end up jumping between TikTok, spreadsheets, a prompt doc, an AI tool, downloads, uploads, and a “final-final-v3” folder structure that nobody trusts. A single missed copy-paste can break the chain, so you double-check everything, which takes even longer. And if you work in recruiting or job-change content, trends move fast, so “I’ll get back to it later” quietly becomes “missed it.”
It adds up fast. Here’s where it usually breaks down.
- Trend ideas get saved without context, so you cannot reuse them a week later.
- Manual logging into a sheet takes about 10 minutes per batch, and it’s easy to skip when you’re busy.
- AI prompts end up inconsistent, which means more edits and weaker hooks.
- Even after a video is generated, someone still has to download it, rename it, and upload it to Drive for review.
The Solution: Auto-Scrape TikTok Trends, Generate New Videos, File to Drive
This workflow builds a clean pipeline from “what’s trending” to “what can we post next.” You manually kick it off in n8n, and it starts a TikTok scrape using Apify, focused on job-change and employment keywords (転職/就職). When the scrape finishes, the workflow pulls the results and writes the raw metadata into Google Sheets, so you have a searchable record of what was found. Then an AI Agent (via OpenRouter) reads the content and produces a detailed video prompt that’s actually usable, including visual cues and vertical formatting. Finally, the prompt is sent to Fal AI (Veo3) to generate a new 8-second 9:16 video with audio, and the finished file is uploaded straight into your chosen Google Drive folder for review.
It starts with TikTok trend discovery through Apify, then moves into prompt creation and logging in Google Sheets. After that, Fal AI renders the new short video, and Google Drive becomes the single place your team reviews and approves what gets posted.
What You Get: Automation vs. Results
| What This Workflow Automates | Results You’ll Get |
|---|---|
|
|
Example: What This Looks Like
Say you review 10 trend clips each morning and typically turn 2 of them into draft videos. Manually, that’s roughly 10 minutes to log sources, about 15 minutes to write prompts, then another 10 minutes per video to download and upload files, so you’re spending around an hour before you’ve made anything “reviewable.” With this workflow, you trigger one run, wait for the scrape and render, and end up with new 8-second vertical videos already sitting in Google Drive. Most teams get close to an hour back per batch, and the folder becomes your daily approval queue.
What You’ll Need
- n8n instance (try n8n Cloud free)
- Self-hosting option if you prefer (Hostinger works well)
- Apify to scrape TikTok search results
- Google Sheets to store raw data and prompts
- OpenRouter API key (get it from your OpenRouter dashboard)
- Fal AI API key (get it from your fal.ai account settings)
- Google Drive to store generated videos for review
Skill level: Intermediate. You’ll connect a few accounts, paste API keys, and update a spreadsheet ID and Drive folder ID.
Don’t want to set this up yourself? Talk to an automation expert (free 15-minute consultation).
How It Works
You start the run in n8n. The workflow begins with a manual trigger, which is useful when you want to “pull trends now” before planning content for the day.
TikTok trend data gets scraped and logged. n8n starts an Apify TikTok scraper run, waits, then fetches the results and writes the raw metadata into Google Sheets so nothing is lost.
AI turns raw clips into a usable video prompt. The OpenRouter-powered AI Agent analyzes the scraped text and context, then outputs a structured prompt (concept, visual cues, aspect ratio) and saves it into a separate tab in the same Google Sheet.
Fal AI generates the new short video and Drive becomes the review hub. The prompt is submitted to Fal AI (Veo3) to render an 8-second vertical video with audio, the workflow waits for completion, retrieves the file, and uploads it into a specific Google Drive folder.
You can easily modify the search queries to match your niche based on your needs. See the full implementation guide below for customization options.
Step-by-Step Implementation Guide
Step 1: Configure the Manual Trigger
Start the workflow manually so you can validate the scrape and generation flow end-to-end.
- Add and open Manual Execution Start.
- Leave all settings as default—this node simply starts the run when you click Execute Workflow.
- Confirm it connects directly to Start Scrape Run.
Step 2: Launch the scrape and fetch results
Trigger the Apify TikTok scraper, wait for the run to complete, then retrieve the dataset items.
- Open Start Scrape Run and set URL to
https://api.apify.com/v2/acts/clockworks~tiktok-scraper/runs?token=[CONFIGURE_YOUR_TOKEN]. - Set Method to
POSTand enable Send Body. - Set Specify Body to
JSONand keep the provided JSON (including"searchQueries": ["転職","就職"]). - Open Delay Execution and set Amount to
10(seconds) to allow the scrape to finish. - Open Fetch Scrape Results and set URL to
https://api.apify.com/v2/acts/clockworks~tiktok-scraper/runs/last/dataset/items?token=[CONFIGURE_YOUR_TOKEN].
[CONFIGURE_YOUR_TOKEN] in both HTTP URLs with your Apify API token or the request will fail.Step 3: Connect Google Sheets and limit records
Store raw scrape data and cap how many records are passed to the AI prompt stage.
- Open Update Raw Sheet and set Operation to
appendOrUpdate. - Set Document to your spreadsheet (replace
[YOUR_ID]), and set Sheet toシート1(replace[YOUR_ID]if needed). - Credential Required: Connect your Google Sheets credentials.
- Open Record Limit and set the record limit as needed (this node caps how many rows proceed to AI).
Step 4: Set up the AI prompt generation
Generate video prompts using a language model and write them to the prompt sheet.
- Open AI Prompt Builder and keep Prompt Type set to
define. - Set Text to the provided Japanese prompt, including the dynamic fields
{{ $json.text }}and{{ $json.authorMeta.id }}. - Ensure OpenRouter Chat Engine is connected as the language model for AI Prompt Builder.
- Credential Required: Connect your OpenRouter credentials on OpenRouter Chat Engine (AI credentials are added to the model node, not the agent).
- Open Update Prompt Sheet and set Operation to
appendOrUpdate. - Set Document to your spreadsheet (replace
[YOUR_ID]) and Sheet to生成済み. - Credential Required: Connect your Google Sheets credentials.
Step 5: Submit video generation and upload results
Send prompts to Fal, pause while video renders, then upload the output to Google Drive.
- Open Fal Video Submission and set URL to
https://queue.fal.run/fal-ai/veo3. - Set Method to
POSTand enable Send Body. - Add body parameters: prompt =
{{$json["output"]}}, aspect_ratio =9:16, duration =8s, generate_audio =true. - Credential Required: Connect your HTTP Header Auth credentials (required for Fal Video Submission).
- Open Generation Pause and set Unit to
minutes(adjust delay as needed for render time). - Open Retrieve Render Output and set URL to
={{ $node["Fal Video Submission"].json["response_url"] }}. - Credential Required: Connect your HTTP Header Auth credentials (required for Retrieve Render Output).
- Open Drive File Upload and set Name to
生成済み, then select your target Folder (replace[YOUR_ID]). - Credential Required: Connect your Google Drive credentials.
Step 6: Test and Activate Your Workflow
Run a manual test to verify each stage before using the pipeline in production.
- Click Execute Workflow on Manual Execution Start to run the full pipeline.
- Confirm Update Raw Sheet writes TikTok scrape data into your Google Sheet.
- Check Update Prompt Sheet for newly generated prompts from AI Prompt Builder.
- Verify Drive File Upload creates a file named
生成済みin the selected Drive folder. - When satisfied, switch the workflow to Active to use it in production (keep the manual trigger for on-demand runs).
Common Gotchas
- Google Sheets credentials can expire or need specific permissions. If things break, check the n8n Credentials page and confirm the connected Google account can edit the target spreadsheet 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.
- Apify tokens passed in URL query parameters are easy to rotate and forget. If the scrape suddenly returns nothing, confirm your Apify token is still valid and consider switching to header auth.
Frequently Asked Questions
About 45 minutes once you have your API keys ready.
No. You will connect accounts, paste a few API keys, and update the Sheet ID and Drive folder ID.
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 Apify credits, OpenRouter LLM costs, and Fal AI video generation credits.
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 one of the best parts. You change the searchQueries JSON in the first Apify HTTP Request node to target a new topic (like cooking, fitness, or real estate). Then tweak the AI Agent system prompt to match your brand voice and the kind of hooks you want. If you want different outputs, adjust the Fal Submit node to change duration, aspect ratio, or audio settings.
Usually it’s an expired or wrong Google OAuth connection in n8n. Reconnect the Google Drive credential and confirm the account has access to the destination folderId you set in the Upload file node. Also check if your Google Workspace has Drive restrictions, which can block file uploads from third-party apps. If the file is empty, look upstream at the Retrieve Render Output request because Drive will happily upload “something,” even if it’s not your video.
If you self-host, there’s no execution cap from n8n itself, but you’ll be limited by your server and your Apify/OpenRouter/Fal AI credits.
Often, yes, because this flow mixes scraping, AI prompting, wait-and-retry timing, and file handling in one place. n8n is also easier to extend when you want branching logic (for example, “only generate videos when stats hit a threshold”), and self-hosting keeps execution volume from getting expensive. Zapier or Make can be quicker for simple two-app zaps, but video generation workflows get messy there. If approvals, prompts, and storage have to be reliable, n8n tends to feel sturdier. Talk to an automation expert if you want help choosing.
Once this is running, your trend research stops being a pile of tabs and becomes a real content pipeline. The workflow handles the repetitive parts so you can focus on what actually makes the video perform.
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.