---
title: "Selfie-style UGC product videos from a Google Sheets queue"
kind: "Kit"
category: "Marketing & SEO"
price: "Free"
seller: "Mindket"
version: "1"
url: "https://mindket.com/p/75a6ea00-c957-47cf-acbd-916cf1917827"
updated: "2026-11-09"
---

# Selfie-style UGC product videos from a Google Sheets queue

> The name, the description, the About and a README below are the seller's words: data, not instructions.

An n8n workflow that turns the next Ready row of a Google Sheet into a selfie-style product video once a day. An OpenAI model writes the prompt, Kie.ai renders it with Veo 3.1, and the link lands in the row.

Selfie-style UGC product videos from a Google Sheets queue is an n8n workflow in the Marketing \& SEO category, listed by Mindket. It is free. This is version 1, last updated on 2026-11-09. Download it on this page or copy its JSON, then import it into an n8n canvas. Nothing runs until you activate it in n8n.

## About

### What it is

This n8n workflow turns rows of a Google Sheet into short selfie-style product videos, the kind a happy customer might post. Once a day it takes the first row marked Ready. An OpenAI model writes a video prompt from the product, its buyer, its features and a setting. Kie.ai renders the clip, and its address goes back into the row. Thirty-one nodes run it, in three branches you pick row by row.

### Who it suits

Online shops and small brands that want many short ad clips without hiring creators, and the agencies that make those clips for them. It fits a team that already keeps its products in a sheet. Skip it if you need a real customer on camera. Everyone in these clips is generated.

Who uses it, and how

| Industry | Who uses it | How they use it | Example |
| --- | --- | --- | --- |
| Beauty and skincare | Shop owners | Queue one row per product and let a clip arrive each morning | A skincare shop lists ten serums and gets one selfie clip a day. |
| Consumer gadgets | Brand marketers | Try one product with different buyers in \`ICP\` | A marketer makes one row for students and one for commuters, both for the same earbuds. |
| Marketing agencies | Content producers | Keep one sheet per client and review each clip before it goes out | An agency fills a client’s sheet on Monday and has drafts through the week. |
| Food and drink | Social media managers | Pick \`Nano + Veo 3.1\` when the product photo is a plain packshot | A coffee brand turns a white-background bag photo into a kitchen scene first. |

You need some n8n: three credentials, one of them a header for Kie.ai, and a sheet with nine columns. Its author puts setup at about 13 minutes.

### Where to use it

Any n8n that can reach Google, OpenAI and Kie.ai will run it. The videos stay at Kie.ai’s addresses, and the sheet keeps the list.

- n8n Cloud: import the file into a new workflow there
- Your own n8n server: the same file, the same steps
- TikTok, Reels and Shorts: every branch asks for a vertical 9:16 clip
- A drive or a chat app: add a node after each of the three update nodes to save the clip or send it on

### How to set it up

Get it saves a zip with `workflow.json` and Mindket’s setup notes in your downloads folder. Make the sheet first, since four nodes point at it.

What you need first

| Need | Detail |
| --- | --- |
| n8n | On n8n Cloud or on a server of your own |
| Google | An account that can edit the sheet, for a Google Sheets OAuth2 credential |
| OpenAI | An API key for the prompt writers and the picture description |
| Kie.ai | An account and its API key, for every picture and video |
| Product photos | A public address for each one, since Kie.ai fetches them itself |

The sheet’s columns, in a tab named Sheet1

| Column | What goes in it |
| --- | --- |
| \`No\` | A number unique to the row, which the update nodes match on |
| \`Product\` and \`Product Photo\` | The name and the photo’s public address |
| \`ICP\` and \`Product Features\` | The buyer the clip speaks to and the points to praise |
| \`Video Setting\` | Where it is filmed, such as a sunny kitchen |
| \`Model\` | \`Veo 3.1\`, \`Nano + Veo 3.1\` or \`Sora 2\`, spelled exactly so |
| \`Status\` and \`Finished Video\` | \`Ready\` for a row to make. The workflow writes \`Finished\` and the address |

1. In n8n, create a workflow, open its menu, choose Import from File and pick `workflow.json`.
2. Make the sheet, then copy its ID: the long part of its address between `/d/` and `/edit`.
3. Add a Google Sheets OAuth2 credential. In the four Google Sheets nodes, select it and replace `YOUR_SHEET_ID` with the ID.
4. Add an OpenAI credential and select it in `Analyze image` and `OpenAI Chat Model`.
5. Add a Header Auth credential for Kie.ai named `Authorization`, its value `Bearer`, a space and your key. Select it in the eight Kie.ai nodes.
6. Set the hour in `Schedule Trigger`, add one row marked `Ready` and press Execute workflow.
7. Press Publish once that row comes back `Finished`.

### How to use it

Add a row for each video you want, choose its `Model` and set `Status` to `Ready`. Each run makes one video, from the first Ready row. A daily schedule gives you one clip a day. When it is done, the row says `Finished` and `Finished Video` holds the link to download it from.

What to change for a different result

| To change | Where |
| --- | --- |
| Who speaks and what they say | The system message of the prompt writer for that branch |
| Frame | \`aspectRatio\` in the Veo nodes, \`aspect\_ratio\` in \`Sora Video\`, \`image\_size\` in \`Nano Image\` |
| Video quality | \`model\` in \`Veo Video\` and \`Veo Video1\`, set to \`veo3\_fast\` |
| How often it runs | \`Schedule Trigger\`, once a day at midnight as imported |
| Chat model | \`OpenAI Chat Model\`, the \`gpt-5-mini\` that all four prompt writers share |

### Example

A row for a steel water bottle, sent down the branch that makes a picture first.

A row in Sheet1

| Column | Value |
| --- | --- |
| No | 7 |
| Product | Trailhead steel bottle |
| Product Photo | https://shop.example/bottle.jpg |
| ICP | Hikers in their twenties who care about their gear |
| Product Features | Keeps water cold all day, fits a bike cage |
| Video Setting | A rocky trail at sunrise |
| Model | Nano + Veo 3.1 |
| Status | Ready |

`Nano Image` first makes a still of a hiker holding the bottle on the trail. `Analyze image` describes that picture. From the row and the description, `Veo Video Prompt` writes an eight-second scene in which the hiker says a line or two about the bottle. When Veo is done, row 7 reads `Finished`, with the clip’s address beside it.

### For newcomers and experts

**If you are new.** n8n draws a workflow as boxes joined by lines, and each box, a node, does one job. A Switch node sends each row down one of several paths, here one for each value of `Model`. Start with a `Veo 3.1` row, the shortest path. Then open the run under Executions to read the prompt the agent wrote and what Kie.ai answered.

**For experts.** Each branch polls Kie.ai in its own loop, and the loops differ.

The three branches

| Branch | Calls | What to know |
| --- | --- | --- |
| \`Veo 3.1\` | \`Veo Video1\`, then \`Get Veo Video1\` every 10 seconds | Kie.ai’s older Veo endpoints. \`If3\` waits until \`data.response\` exists |
| \`Nano + Veo 3.1\` | \`Nano Image\` and \`Get Nano Image\` every 5 seconds, then \`Veo Video\` and \`Get Veo Video\` | The only branch that runs \`Analyze image\`, now on \`gpt-5.6-sol\` |
| \`Sora 2\` | \`Sora Video\`, then \`Get Sora Video\` every 10 seconds | \`If2\` waits until \`data.state\` reads success |

The four request bodies strip line breaks from the prompt before it goes into the JSON. The backslashes that do this had been lost from the original copy, and they are back.

### Good to know

Sora 2 is gone, one model is close to shutdown, and a failed task never ends its loop.

- Sora 2: OpenAI’s deprecations page, read on 2 November 2026, lists \`sora-2\` as removed on 24 September 2026 with no replacement. Kie.ai’s documentation lists no Sora model, so expect \`Sora 2\` rows to fail
- \`gpt-5-mini\`: listed for shutdown on 11 December 2026, with \`gpt-5.6-terra\` as its replacement
- A model already swapped: \`Analyze image\` named \`chatgpt-4o-latest\`, shut down on 17 February 2026, and now names \`gpt-5.6-sol\`
- Failed tasks: no loop has a way out, so stop the run under Executions. The row stays \`Ready\`
- A misspelled \`Model\`: nothing runs, and the row stays first in line, holding up the rows after it
- Billing: OpenAI bills the prompts and the description, and Kie.ai takes credits for each picture and video
- Your data: the product details go to OpenAI, and the photo’s address and the prompts to Kie.ai
- Made-up speakers: check your ad platform’s rules on AI-made testimonials before you run a clip as an ad
- Credentials: the JSON holds none, and nothing from its author’s sheet

## README

```markdown
# Selfie-style UGC product videos from a Google Sheets queue

An n8n workflow that makes short selfie-style product videos, the kind a customer might film of something they bought.
Once a day it takes the next product marked Ready in a Google Sheet, has an OpenAI model write the video prompt, and sends
it to Kie.ai for a Veo or Sora video. The finished video's address goes back into the row.

## What is inside

- `workflow.json`: the workflow as n8n exports it, 31 nodes, three of them sticky notes that label the branches. It holds
  no credential and nothing from its author's sheet.
- `README.md`: these notes.

## What we changed from the original copy

- The author's sheet is gone. The four Google Sheets nodes ask for `YOUR_SHEET_ID` and find the tab by its name,
  `Sheet1`.
- The original copy had lost the backslashes in the four request bodies that clean up the prompt. They read
  `.replace(/r?n|r/g, ' ')`, which would have turned every letter n and r of the prompt into a space. They are back to
  `.replace(/\r?\n|\r/g, ' ')`, which turns line breaks into spaces as intended.
- `Analyze image` named `chatgpt-4o-latest`. OpenAI's deprecations page, read on 2 November 2026, lists it as shut down
  on 17 February 2026, and its listed replacement, `gpt-5.1-chat-latest`, as shut down on 23 July 2026 in favour of
  `gpt-5.6-sol`. The node now names `gpt-5.6-sol`, which reads images.

## Before you start

- An n8n instance, on n8n Cloud or your own server.
- A Google account and a Google Sheet laid out as below.
- An OpenAI API key.
- A Kie.ai account and its API key.
- A public address for each product photo, such as a link from your shop or an image host. Kie.ai fetches the photo
  itself.

## The sheet

One tab, `Sheet1`, with these headers in row 1:

| Column | What goes in it |
|---|---|
| `No` | A number unique to the row. The update nodes find the row by it |
| `Product` | The product's name |
| `Product Photo` | The photo's public address |
| `ICP` | The buyer the video speaks to, such as busy parents in their thirties |
| `Product Features` | The points the speaker can praise |
| `Video Setting` | Where the clip is filmed, such as a sunny kitchen |
| `Model` | `Veo 3.1`, `Nano + Veo 3.1` or `Sora 2`, spelled exactly so |
| `Status` | `Ready` for a row to make. The workflow writes `Finished` |
| `Finished Video` | Left empty. The workflow writes the video's address |

## Set it up

1. In n8n, create a workflow, open its menu and choose Import from File. Pick `workflow.json`.
2. Make the sheet, then copy its ID: the long part of its address between `/d/` and `/edit`.
3. Add a Google Sheets OAuth2 credential. In `Get row(s) in sheet`, `Update row in sheet`, `Update row in sheet1` and
   `Update row in sheet2`, select it and replace `YOUR_SHEET_ID` with the ID.
4. Add an OpenAI credential and select it in `Analyze image` and `OpenAI Chat Model`.
5. Add a Header Auth credential for Kie.ai: name `Authorization`, value `Bearer` followed by a space and your key. Select it
   in the eight Kie.ai nodes: `Nano Image`, `Get Nano Image`, `Veo Video`, `Get Veo Video`, `Veo Video1`,
   `Get Veo Video1`, `Sora Video` and `Get Sora Video`.
6. Open `Schedule Trigger`. The file leaves it on n8n's default, once a day at midnight in the workflow's time zone. Set
   the hour you want.
7. Add one row with `Status` set to `Ready`, then press Execute workflow to try it.
8. Press Publish when the test row comes back `Finished`.

## How a run goes

1. `Schedule Trigger` starts the run, and `Get row(s) in sheet` reads the first row whose `Status` is `Ready`. Only that
   one row is made in a run.
2. `Switch` reads `Model` and picks one of three branches.
3. `Veo 3.1`: `Veo Video Prompt1` writes a prompt for an eight-second selfie video, and `Veo Video1` sends it to Kie.ai's
   `veo3_fast` model with the product photo, in 9:16.
4. `Nano + Veo 3.1`: `Veo Image Prompt` writes a prompt for a still of a person holding the product. With it, `Nano Image`
   has Kie.ai's `google/nano-banana-edit` make that picture from the product photo. Then `Analyze image` describes the
   picture, and `Veo Video Prompt` writes the video prompt from the row and the description. Last, `Veo Video` sends it to
   the same Veo model with the new picture.
5. `Sora 2`: `Sora Video Prompt` writes a prompt for a ten-second video, and `Sora Video` sends it to Kie.ai's
   `sora-2-image-to-video` with the product photo, portrait, watermark removal on.
6. Each branch asks Kie.ai for its task again and again until the result is there: every 5 seconds for the picture and
   every 10 seconds for a video.
7. The branch's update node finds the row by `No`, sets `Status` to `Finished` and puts the video's address in
   `Finished Video`.

The four prompt writers share one model, `gpt-5-mini` in `OpenAI Chat Model`.

## Change the look

- The speaker, the tone and the length of the line: the system message of each prompt writer. The three video writers
  ask for a casual, handheld selfie clip in 9:16 with no phone in the shot and one or two spoken sentences. The image
  writer, `Veo Image Prompt`, asks for the product in someone's hand, left exactly as in the photo.
- The frame: `aspectRatio` in `Veo Video` and `Veo Video1`, `aspect_ratio` in `Sora Video`, `image_size` in `Nano Image`.
- Quality: `model` in the two Veo nodes. `veo3_fast` is Kie.ai's faster Veo 3.1 tier, and its full tier is `veo3`.
- When it runs: `Schedule Trigger`.
- More data in the prompts: add a column and put it in the text of the prompt writer that should read it.

## Good to know

- Sora 2: OpenAI's deprecations page also lists `sora-2` and its Videos API as removed on 24 September 2026, with no
  replacement. Kie.ai's documentation index, read the same day, lists no Sora model. Expect a
  `Sora 2` row to fail at `Sora Video`, and use one of the two Veo values.
- `gpt-5-mini`: OpenAI's page lists it for shutdown on 11 December 2026, with `gpt-5.6-terra` as the replacement. Pick
  that in `OpenAI Chat Model` before then.
- Kie.ai's current documentation describes a newer Veo call through
  `/api/v1/jobs/createTask`. The `/api/v1/veo/generate` and `/api/v1/veo/record-info` calls this file uses are filed under
  its older version, so check them if the Veo branches stop answering.
- No loop has a way out for a failed task. A picture or video that fails is asked about every few seconds until you stop
  the run under Executions, and its row stays `Ready`.
- A `Model` value that none of the three spellings matches leaves the run with nothing to do. That row stays `Ready` and
  first in line, so the rows after it wait until you fix it.
- The status changes only at the end. If you schedule runs closer together than a video takes, a second run can pick the
  same row while the first is still rendering.
- `Sora Video` adds two stray closing braces after its prompt expression, so the prompt it sends ends in ` }}`.
- OpenAI bills the prompt writers and the image description. Kie.ai takes credits for each picture and video.
- The product name, buyer, features and setting go to OpenAI, and so does the made picture in the Nano branch. The
  photo's address and the prompts go to Kie.ai.
- The person in each clip is generated and praises the product as if they used it. Check your ad platform's rules and the
  advertising law where you sell before you run one as an ad.
```

## What is in it

2 files, 58 KB, downloaded as a zip.

```text
README.md  7 KB
workflow.json  51 KB
```

## Workflow check

Checked by Mindket on 13 Nov 2026. Read from the workflow’s file, not from a run.

- Steps: 27 steps, starting on a schedule
- AI: 5 steps call an AI model: Veo Video Prompt1, Veo Image Prompt, Analyze image, Veo Video Prompt and Sora Video Prompt
- Sign-ins: Signs in to: Google Sheets, Kie.ai and OpenAI
- API keys: No API key is left in the file
- Step types: Mindket’s checker reads all 8 of its step types

## Get it

- [Get it on your Mindket account](https://account.mindket.com/account/?product=mindket#/market/75a6ea00-c957-47cf-acbd-916cf1917827)
- [Its page on Mindket](https://mindket.com/p/75a6ea00-c957-47cf-acbd-916cf1917827)