Auto-Generate Instagram Reels with n8n: Veo3 + GPT Video Ad Workflow

Enter a product or trend → GPT generates video prompt → Veo3 creates 9:16 short video → GPT writes caption → auto-log to Google Sheets

Who

Marketers, creators, or content teams who want to build an automated short-form video ad pipeline in n8n

You get

Trigger via chat to generate an Instagram Reel with caption and log results to Google Sheets

You need

n8n · google-sheets

Steps

1. Set up Chat Trigger

   Add a Chat Trigger node (@n8n/n8n-nodes-langchain.chatTrigger) to the workflow. Keep default options. This receives user input describing a product, theme, or trend. Activate the workflow and send a chat message to trigger execution.

2. Configure Video Prompt Engineer Node

   Add an OpenAI node and select model chatgpt-4o-latest. In Messages, add the system prompt and user prompt. The system prompt defines the video prompt generation rules; the user prompt references upstream chat input {{ $json.chatInput }}.

   Execution prompt · Source text。OpenAI node Prompt Engineer system message field

   Copy prompt

   You are a creative video prompt generator for short-form ads (e.g., Instagram, TikTok). Based on:
   
   The chat input of the user
   
   Your task is to craft a concise, visually descriptive video generation prompt suitable for input into the Seedance API.
   
   🛑 Do not include any extra explanation, formatting, or commentary. Your entire output must be the exact prompt to pass into the video generator.
   
   The prompt should:
   – Be under 100 words
   – Describe the visual elements, tone, and motion clearly
   – Reflect the product or brand type, and
   – Incorporate the marketing trend as the core concept or hook
   
   Example of your expected output format:
   
   “A close-up slow-motion shot of a glass perfume bottle as morning sunlight filters through mist. The background shows soft-focus wildflowers, matching the theme of natural beauty and calm. Overlay text: ‘Nature’s Elegance. Reinvented.’ Trend-inspired styling based on the ‘quiet luxury’ aesthetic. For Instagram. 5 seconds.”

   Execution prompt · Source text。OpenAI node Prompt Engineer user message field

   Copy prompt

   ={{ $json.chatInput }}

3. Submit Video Generation Request and Wait

   Add an HTTP Request node (Veo3 Post Request), method POST, URL https://api.wavespeed.ai/api/v3/google/veo3-fast. Authentication: genericCredentialType → httpHeaderAuth. Body parameters: aspect_ratio=9:16, duration=8, enable_prompt_expansion=true, generate_audio=false, prompt referencing previous step output {{ $json.message.content }}. Connect a Wait node set to 30 seconds to allow the job to enter the processing queue.

4. Poll for Video Result

   Add a second HTTP Request node (Veo3 Get Request), method GET, URL https://api.wavespeed.ai/api/v3/predictions/{{ $json.data.id }}/result, also using httpHeaderAuth. Connect an If node checking whether {{ $json.data.status }} equals processing: if true, route through a Wait 30 secs node and query again; if false, proceed to the next step.

5. Generate Instagram Caption

   Add a second OpenAI node, select model gpt-4.1. The system prompt defines an Instagram caption copywriter role; the user prompt references the Prompt Engineer output to generate an impactful caption.

   Execution prompt · Source text。OpenAI node Caption Generator system message field

   Copy prompt

   You're an Instagram Caption copywriter. You'll receive a set of video prompt message that is used for generating an Instagram 5 second reel video. Your job is to write an effective accompanying caption. Language style should be playful and impactful.

   Execution prompt · Source text。OpenAI node Caption Generator user message field

   Copy prompt

   =Based on this video generation prompt, create an impactful accompanying caption for the Instagram Post {{ $('Prompt Engineer').item.json.message.content }}

6. Log to Google Sheets

   Add a Google Sheets node, operation Append. Configure documentId and sheetName to point to your target spreadsheet. Column mappings: Video Description / Prompt = {{ $('Prompt Engineer').item.json.message.content }}; Video URL (google drive) = {{ $('If').item.json.data.outputs[0] }}; Caption = {{ $json.message.content }}; Status = Ready to Post. Each execution appends a new row.

You are recreating n8n template 5849: Veo3 Instagram Reel Generator. First confirm you have these credentials: OpenAI API, Wavespeed (Veo3) API Key (HTTP Header Auth), and Google Sheets OAuth2. Then configure the nodes in order: Chat Trigger → Prompt Engineer (chatgpt-4o-latest) → Veo3 Post Request → Wait → Veo3 Get Request → If (polling loop) → Caption Generator (gpt-4.1) → Google Sheets. Note: the Veo3 Post body parameter prompt must reference the Prompt Engineer output; Google Sheets documentId and sheetName must be set to real values.