# Generate Mind-Bending 'What If' Videos with Google Veo 3: n8n workflow

> Started by an event in a connected app, and works across Google Cloud Storage and Telegram. It hands the judgement calls to DeepSeek and Gemini.

Source: https://millionrounds.com/workflow/generate-mind-bending-what-if-videos-with-google-veo-3 (Millionrounds; every figure on the page links to its filing or article)

[Automation library](https://millionrounds.com/workflows) · [Content](https://millionrounds.com/workflows?category=Content#library)

# Generate Mind-Bending 'What If' Videos with Google Veo 3

Started by an event in a connected app, and works across Google Cloud Storage and Telegram. It hands the judgement calls to DeepSeek and Gemini. 60 steps, 5 branches, 5 loops or waits: large, and worth reading before you trust it with anything live.

Large Calls a model: DeepSeek, Gemini

[Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Fgenerate-mind-bending-what-if-videos-with-google-veo-3)

**60 steps** Large: read it before trusting it with anything live

**5** Branches: places the flow splits

**5** Loops or waits

**2** Services it connects to

## The flow

Starts it 1 Model 12 Logic 13 Service 34

The steps in the order they run, from what starts it.

- 1 **Trigger Manual Workflow** Manual trigger *Starts it*
- 2 **Google Chat Model 1** Lm Chat Google Gemini *Model*
- 3 **DeepSeek Chat Model** Lm Chat Deep Seek *Model*
- 4 **Google Chat Model 2** Lm Chat Google Gemini *Model*
- 5 **Google Chat Model 3** Lm Chat Google Gemini *Model*
- 6 **Google Chat Model 4** Lm Chat Google Gemini *Model*
- 7 **Google Chat Model 5** Lm Chat Google Gemini *Model*
- 8 **Set Input Variables** Set *Logic*
- 9 **Create Story** Chain Llm *Model*
- 10 **Parse Structured Output** Output Parser Structured *Model*
- 11 **Prepare Hook Prompt** Chain Llm *Model*
- 12 **Prepare Segment 1 Prompt** Chain Llm *Model*
- 13 **Prepare Segment 2 Prompt** Chain Llm *Model*
- 14 **Prepare CTA Prompt** Chain Llm *Model*
- 15 **Set API Parameters** Set *Logic*
- 16 **Generate JWT Token** Jwt *Service*
- 17 **Fetch OAuth Token** Http Request *Service*
- 18 **Post Audio Synthesis** Http Request *Service*
- 19 **Convert Audio to File** Convert To File *Service*
- 20 **Upload Hook Audio File** Google Cloud Storage *Service*
- 21 **Post Audio Synthesis 1** Http Request *Service*
- 22 **Convert Audio File 1** Convert To File *Service*
- 23 **Upload Audio Segment 1** Google Cloud Storage *Service*
- 24 **Post Audio Synthesis 2** Http Request *Service*
- 25 **Convert Audio File 2** Convert To File *Service*
- 26 **Upload Audio Segment 2** Google Cloud Storage *Service*
- 27 **Post Audio Synthesis 3** Http Request *Service*
- 28 **Convert Audio File 3** Convert To File *Service*
- 29 **Upload CTA Audio File** Google Cloud Storage *Service*
- 30 **Post Video Generation 1** Http Request *Service*
- 31 **Wait 20 Seconds 1** Wait *Logic*
- 32 **Fetch Video Status 1** Http Request *Service*
- 33 **Route Based on Rule 1** Switch *Logic*
- 34 **Convert Video File 1** Convert To File *Service*
- 35 **Upload Video Hook File** Google Cloud Storage *Service*
- 36 **Post Video Generation 2** Http Request *Service*
- 37 **Wait 20 Seconds 2** Wait *Logic*
- 38 **Fetch Video Status 2** Http Request *Service*
- 39 **Route Based on Rule 2** Switch *Logic*
- 40 **Convert Video File 2** Convert To File *Service*
- 41 **Upload Video Segment 1** Google Cloud Storage *Service*
- 42 **Post Video Generation 3** Http Request *Service*
- 43 **Wait 20 Seconds 3** Wait *Logic*
- 44 **Fetch Video Status 3** Http Request *Service*
- 45 **Route Based on Rule 3** Switch *Logic*
- 46 **Convert Video File 3** Convert To File *Service*
- 47 **Upload Video Segment 2** Google Cloud Storage *Service*
- 48 **Post Video Generation 4** Http Request *Service*
- 49 **Wait 20 Seconds 4** Wait *Logic*
- 50 **Fetch Video Status 4** Http Request *Service*
- 51 **Route Based on Rule 4** Switch *Logic*
- 52 **Convert Video File 4** Convert To File *Service*
- 53 **Upload Video CTA File** Google Cloud Storage *Service*
- 54 **Build Creatomate Request** Code *Logic*
- 55 **Merge Video Files** Http Request *Service*
- 56 **Wait for Rendering** Wait *Logic*
- 57 **Check Render Completion** Http Request *Service*
- 58 **Route Based on Completion** Switch *Logic*
- 59 **Download Final Video** Http Request *Service*
- 60 **Send Video via Telegram** Telegram *Service*

## How it's built

- **Starts on:** An event in a connected app
- **Steps:** 60, with 5 branches, 5 loops or waits
- **Size:** Large: read it before trusting it with anything live
- **Connects to:** Google Cloud Storage, Telegram
- **Model:** DeepSeek, Gemini

## Questions

What does it need to run?

An n8n account, plus your own Google Cloud Storage and Telegram accounts, and a key for DeepSeek and Gemini. You connect your own accounts after importing it; none are included.

What starts it?

It starts on an event in a connected app.

Does it use AI?

Yes. It calls DeepSeek and Gemini. Model calls are billed by the provider, not by n8n.

How long does it take to set up?

Take your time. At 60 steps it is large: read it before trusting it with anything live.

How do I import it?

Copy the workflow, open a new workflow in n8n and paste. The steps appear on the canvas, ready for your own accounts.

**Before you run it**

Nothing here has been tested by us. It is somebody's working automation, read and described from its own steps. Treat the connections it wants as a list of accounts it will touch, and read the 60 steps before you point it at anything that matters.

## Run it in n8n

- **Create your n8n account** Free to start. n8n is where the workflow runs. [Create an n8n account ↗](https://millionrounds.com/n8n)
- **Download the workflow** Free with a Millionrounds account. [Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Fgenerate-mind-bending-what-if-videos-with-google-veo-3)
- **Paste it into n8n** Open a new workflow in n8n and paste. Then connect your own accounts.

Stored with the author's traces removed: canvas notes, instance identifiers, saved credential names and any live document they had left behind.

## Connects to

Each opens the other workflows that use it.

[Google Cloud Storage](https://millionrounds.com/workflows?service=Google+Cloud+Storage#library)[Telegram](https://millionrounds.com/workflows?service=Telegram#library)

## Workflows like it

Also content, with the same services where possible, closest in size first.

- [**Generate AI songs + music videos with Gemini and OpenAI** 57 steps · calls a model · Google Drive, Google Sheets](https://millionrounds.com/workflow/generate-ai-songs-music-videos-with-gemini-and-openai)
- [**Automated NASA Image & Content Publisher** 55 steps · calls a model · LinkedIn, RSS](https://millionrounds.com/workflow/automated-nasa-image-and-content-publisher)
- [**FB Ad Spy: AI-Powered Competitor Ad Intelligence & Auto-Video** 54 steps · calls a model · Google Cloud Storage, Google Drive](https://millionrounds.com/workflow/fb-ad-spy-ai-powered-competitor-ad-intelligence-and-auto-vid)
- [**AI Agents Generate Content & Automate Posting** 46 steps · calls a model · Google Drive, Google Sheets](https://millionrounds.com/workflow/ai-agents-generate-content-and-automate-posting-3)
- [**AI Agents Generate Content & Automate Posting** 46 steps · calls a model · Google Drive, Google Sheets](https://millionrounds.com/workflow/ai-agents-generate-content-and-automate-posting)
- [**AI Agents Generate Content & Automate Posting** 46 steps · calls a model · Google Drive, Google Sheets](https://millionrounds.com/workflow/ai-agents-generate-content-and-automate-posting-2)