Convert natural language to video JSON prompts with GPT and Gemini for Veo 3
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 AI workflow has 6 nodes and runs when a chat message arrives. Along the way it connects Google Gemini, Azure OpenAI Chat Model and OpenRouter Chat Model.
How it runs
Trigger: When a chat message arrives.
- Prompt converter (Basic LLM Chain): sends a prompt to an LLM, with model: Openai; output parser: Json parser
- Generate a video (Google Gemini): work with video
- Alternative (OpenRouter Chat Model): uses OpenRouter Chat Model
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 (6)
- Google Gemini
@n8n/n8n-nodes-langchain.googleGemini - Structured Output Parser
@n8n/n8n-nodes-langchain.outputParserStructured - Azure OpenAI Chat Model
@n8n/n8n-nodes-langchain.lmChatAzureOpenAi - Chat Trigger
@n8n/n8n-nodes-langchain.chatTrigger - Basic LLM Chain
@n8n/n8n-nodes-langchain.chainLlm - OpenRouter Chat Model
@n8n/n8n-nodes-langchain.lmChatOpenRouter
From the author
Turn plain-language video ideas into ready-to-use Veo 3 JSON prompts. This workflow takes your free-text prompt, refines it with Langchain AI and Google Gemini, and returns structured JSON tuned for Veo 3 video generation. No manual formatting, no guessing…