The flow
Starts it 1Model 7Service 8
The steps in the order they run, from what starts it.
- 1 🔎 Parse Blog Metadata OutputOutput Parser StructuredModel
- 2 🧠 Article Writer (LLaMA)Lm Chat Open RouterModel
- 3 🧠 Article Writer (Gemini)Lm Chat Google GeminiModel
- 4 🧠 Article Writer (GPT-4 mini)Lm Chat Open AiModel
- 5 🔖 Metadata Generator (Nemotron)Lm Chat Open RouterModel
- 6 ⏱️ Auto Trigger (Every 3 Hours)Schedule triggerStarts it
- 7 🔖 Generate Blog MetadataChain LlmModel
- 8 ✍️ Compose SEO Article ContentChain LlmModel
- 9 📝 Create WordPress Draft PostWordpressService
- 10 🔍 Set Yoast SEO MetadataHttp RequestService
- 11 🖼️ Generate Featured Image (Runware)Http RequestService
- 12 📥 Fetch Generated ImageHttp RequestService
- 13 📤 Upload Image to WordPress MediaHttp RequestService
- 14 📎 Attach Image to PostHttp RequestService
- 15 📣 Send Notification to DiscordDiscordService
- 16 📨 Send Notification to TelegramTelegramService
How it's built
- Starts on
- A clock
- Steps
- 16
- Size
- Medium: a working afternoon
- Connects to
- Discord, Telegram, WordPress
- Model
- Gemini, OpenAI, OpenRouter
Questions
What does it need to run?
An n8n account, plus your own Discord, Telegram and WordPress accounts, and a key for Gemini and OpenAI. You connect your own accounts after importing it; none are included.
What starts it?
It starts on a clock.
Does it use AI?
Yes. It calls Gemini, OpenAI and OpenRouter. Model calls are billed by the provider, not by n8n.
How long does it take to set up?
Plan an afternoon. 16 steps is enough that you should read each one before running it.
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 itNothing 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 16 steps before you point it at anything that matters.