Annotate video scripts with DeepSeek, Kie.ai, Google Sheets and Google Drive
Ready for 3.0Ready for 3.0. This template uses no nodes that n8n 3.0 removes. No removed nodes, versions or helpers found. Static check, last run 2026-10-19.
What this workflow does
This workflow has 22 nodes and runs when someone submits an n8n form (“Video Overlay Placement”). Along the way it connects Google Sheets and Google Drive. It also calls api.deepseek.com and api.kie.ai over HTTP.
How it runs
Trigger: When someone submits an n8n form (“Video Overlay Placement”).
- Retrieve Style Memory from Sheets (Google Sheets): uses Google Sheets
- Select Most Recent Memory (Code): runs custom JavaScript code
- Set Script Instructions (Edit Fields (Set)): sets 2 fields: videoScript, activeInstructions
- Post Visual Segments Request (HTTP Request): calls api.deepseek.com (POST)
- Parse Visual Segments (Code): runs custom JavaScript code
- Filter: keeps only the items that match a condition
- Process Segments in Batches (Loop Over Items (Split in Batches)): loops over the items in batches
- Aggregate Segment Data (Code): runs custom JavaScript code
- Submit Image Task to Kie.ai (HTTP Request): calls api.kie.ai (POST)
- Format Final Script (Code): runs custom JavaScript code
…plus 11 more steps. See the full node list below.
Services it uses
HTTP calls to: api.deepseek.com, api.kie.ai
Before you upgrade to n8n 3.0
Nothing in this workflow is removed in n8n 3.0, so it should import and run after the upgrade.
Nodes used (10)
- n8n Form Trigger
n8n-nodes-base.formTrigger - Google Sheets
n8n-nodes-base.googleSheets - Code
n8n-nodes-base.code - Edit Fields (Set)
n8n-nodes-base.set - HTTP Request
n8n-nodes-base.httpRequest - Filter
n8n-nodes-base.filter - Loop Over Items (Split in Batches)
n8n-nodes-base.splitInBatches - Wait
n8n-nodes-base.wait - If
n8n-nodes-base.if - Google Drive
n8n-nodes-base.googleDrive
From the author
Quick overview Give it a video script and it figures out exactly where visuals belong, generates them with AI, and hands back the finished script with images in place. It even remembers your placement style, so it needs less guidance every time you use it.…