ClaudeCreativeVideoAI score · 67/100AI-assisted edit · no obvious prompt-injection riskn8n.io

n8n Auto YouTube Shorts: Flux + Runway + Creatomate Pipeline

Read ideas from Google Sheets → AI-generate images/animation/audio → merge and render → auto-upload to YouTube

Some experienceStepsWorkflowTip
Who
Creators or operators who need to produce short videos in batches
You get
One n8n workflow automates the full video pipeline from idea to publishing
You need
n8n · google-sheets · runwayml · elevenlabs · creatomate

Constraints

Prerequisites: n8n cloud or self-hosted instance; Google Sheets with specified column names; API keys for Anthropic Claude / Google Gemini, Flux AI (RapidAPI), RunwayML, ElevenLabs, Creatomate, and YouTube API configured as n8n credentials. Costs: each API provider bills independently; specific pricing unknown.

What they did

Author mjomba published an automated video creation workflow in the n8n official template library. The workflow uses Google Sheets as the idea source, reads each pending idea, then calls Claude/Gemini for prompt generation, Flux AI for images, RunwayML for animation, ElevenLabs for narration and sound effects, Creatomate for merging and rendering, and finally uploads via the YouTube API while writing status back to the sheet.

How it went

The author reports that the workflow delivers a "fully automated video creation pipeline, reducing manual effort and optimizing content production" (author_report). This site has not verified runtime results.

Worth knowing

1. All nodes in workflow.json have empty parameters objects; after import you must manually configure each API endpoint, authentication, and parameters. 2. The source does not provide full system/user prompt text for the agent nodes; prompts for Image Prompt Agent and Audio Prompt Agent must be written yourself. 3. API services (Flux RapidAPI, RunwayML, ElevenLabs, Creatomate) bill independently; pricing is unspecified. 4. Wait nodes (20 seconds / 1 minute / 25 Seconds) reflect the author's experience; actual render time may vary with queue depth. 5. To change animation style, update the style column in Google Sheets and adjust the prompt generation logic in n8n. 6. To add subtitles, configure the Creatomate rendering step additionally.

n8n workflow template

Structure checked · Not run-tested

Use “Import from File” in n8n, or copy the JSON and paste it into the editor. Connect your own accounts, then try test data. The template is inactive by default.

Download JSONOriginal template

Setup and test checklist

Credentials to connect

  • After import, connect your own credentials on auth-required nodes; author secrets are not included.

Configuration to replace

  • Source template is n8n public workflow #3416 (~32 nodes). Keep inactive after import; verify triggers, expressions and external API endpoints.
  • Sticky-note guidance is informational; replace placeholders with your own accounts, sheet schemas or channel IDs.

Test input and expected output

  • Manually run the main path once in a test workspace and confirm credentialed nodes authenticate without errors.
  • Drive one synthetic/redacted sample through and check output fields and downstream writes before enabling in production.

Template changes

  • Author credential bindings, webhookId and execution data are removed; the workflow is inactive. Nodes, connections and original prompts are preserved. Not run-tested in n8n.
  • No business-logic edits; verify keys, quotas and privacy compliance before use.

Template retrieved: 2026-10-24

Steps

  1. Extract idea and generate prompts

    In n8n, configure the Google Sheets node (Grab Idea) to read the first row where videoStatus = 'To Do' and mark it as Processing. Then use the AI Agent node (Image Prompt Agent) with Anthropic Claude or Google Gemini to generate image and audio prompts based on the idea, style, and other fields. Corresponding nodes in workflow.json: Grab Idea → Set Idea → Image Prompt Agent → Remove \n → Set Prompts.

  2. Generate image with Flux AI

    Pass the image prompt to the HTTP Request node (Image Generation) to call the Flux AI API and generate a high-quality image. Corresponding nodes in workflow.json: Set Prompts → Image Generation → 20 seconds (Wait) → Get Images.

  3. Animate image with RunwayML

    Send the generated image via the HTTP Request node (Generate Videos) to the RunwayML API to produce an animated video. Wait about 1 minute (Wait node), then retrieve the result via Get Videos. Corresponding nodes in workflow.json: Get Images → Generate Videos → 1 minute (Wait) → Get Videos.

  4. Generate audio with ElevenLabs

    Use the AI Agent node (Audio Prompt Agent, connected to Google Gemini / Flash 2.0) to generate an audio prompt, then shape parameters via the Set Audio node, and call the ElevenLabs API via the HTTP Request node (Generate Audio) to produce narration and sound effects. Corresponding nodes in workflow.json: Update Video Status → Audio Prompt Agent → Set Audio → Generate Audio → Upload to Drive → Share File.

  5. Merge and render with Creatomate

    Merge the video and audio streams via the Merge node, then call the Creatomate API via the HTTP Request node (Render Video1) to render the final video. Wait about 25 seconds, then download the finished file via Download Video. Corresponding nodes in workflow.json: Merge → Render Video1 → 25 Seconds (Wait) → Download Video.

  6. Upload to YouTube and update status

    Upload the final video via the YouTube node (Upload Video), then update the Google Sheet via the Google Sheets node (Update Sheet) to set videoStatus to Created and publishStatus to Processed. Corresponding nodes in workflow.json: Download Video → Upload Video → Update Sheet.

Prompt you can copy

Setup guidance · Editorial suggestion。Hand to setup assistant; confirm inputs and permissions first

This block is the prompt. Ads are never placed here.

You are setting up the n8n template "Generate AI YouTube shorts with Flux, Runway, Eleven Labs and Creatomate" (ID 3416). Proceed in this order: 1) Confirm your n8n instance is available; 2) Create a Google Sheet with columns: title, bibleverse, idea, style, caption, videoStatus, publishStatus; 3) Configure credentials in n8n Settings → Credentials for Claude/Gemini, Flux AI (RapidAPI), RunwayML, ElevenLabs, Creatomate, YouTube API, Google Sheets, and Google Drive; 4) Import workflow.json or build manually from the node list; 5) Before testing, ensure at least one row has videoStatus = 'To Do'.

After importing the template, fill in URL, Header, and Body for each HTTP Request node per the latest provider docs; node-internal prompts must be configured manually

Source

Generate AI YouTube shorts with Flux, Runway, Eleven Labs and Creatomate · mjomba · n8n.io · 2025-04-03

Comments & feedback

Tried this method? Share results, problems or improvements. Comments appear after moderation. Please avoid sensitive information.

Loading…

    Related