AI video automation engine - generate & publish YT shorts with Veo-3 or Sora 2
Ready for 3.0What this workflow does
This AI workflow has 16 nodes and runs on a schedule (every day). Along the way it connects YouTube, Google Gemini Chat Model and Telegram.
How it runs
Trigger: On a schedule (every day).
- Filenames + topic (Edit Fields (Set)): sets or maps fields
- Video Idea (Perplexity): uses Perplexity
- Prompt & Text Agent (AI Agent): runs an AI agent, with model: Google Gemini Chat Model; output parser: Structured Output Parser
- Start Videogeneration (HTTP Request): calls an HTTP API
- Wait: pauses before continuing
- Get Videogeneration (HTTP Request): calls an HTTP API
- Videogeneration finished (If): checks a condition and branches into true / false
- Download Video (HTTP Request): calls an HTTP API
- Write Video on Disk (Read/Write Files from Disk): reads a file from disk
- Edit Video (Execute Command): runs a shell command on the n8n host
…plus 3 more steps. See the full node list below.
Services it uses
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 (13)
- YouTube
n8n-nodes-base.youTube - Schedule Trigger
n8n-nodes-base.scheduleTrigger - Google Gemini Chat Model
@n8n/n8n-nodes-langchain.lmChatGoogleGemini - Structured Output Parser
@n8n/n8n-nodes-langchain.outputParserStructured - Perplexity
n8n-nodes-base.perplexity - AI Agent
@n8n/n8n-nodes-langchain.agent - HTTP Request
n8n-nodes-base.httpRequest - If
n8n-nodes-base.if - Read/Write Files from Disk
n8n-nodes-base.readWriteFile - Execute Command
n8n-nodes-base.executeCommand - Telegram
n8n-nodes-base.telegram - Edit Fields (Set)
n8n-nodes-base.set - Wait
n8n-nodes-base.wait
From the author
Product Overview Scale short-form content without scaling your team. This template turns idea discovery → prompt & text generation → Veo-3 video rendering → vertical formatting → multi-channel publishing into one cohesive pipeline. It’s built natively on n8n,…