Generate Videos from Text Prompts using GPT-5 and Google Veo-3

Description

This workflow contains community nodes that are only compatible with the self-hosted version of n8n.

🎬 GPT-5 Cinematic Video Generator (n8n + AI/ML API + Google Veo-3)
This n8n workflow transforms even a single word into a fully rendered cinematic video using Google Veo-3 image-to-video and prompt expansion with GPT-5. Ideal for rapid creative prototyping, content creation, and AI-driven video production.

🚀 Key Features

Ultra-Short Input Ready** – Works with just one keyword or a short idea.
AI Prompt Expansion** – GPT-5 adds cinematic elements: camera motion, mood, color palette, and composition.
Automated Video Generation** – Veo-3 i2v model creates smooth, visually appealing clips.
Smart Polling** – Waits until video is ready, with success/fail handling.
Direct Output** – Returns ready-to-use video URL for download or publishing.

🛠 Setup Guide

Create AI/ML API Credentials

Get your API key from AI/ML API Keys.
In n8n > Credentials, add AI/ML account (Bearer token).

(Optional) Change Image Source

Edit the Set image URL node to point to your desired still image for video generation.

Run from Chat

Send a word or short phrase via Chat Trigger to start the process.

(Optional) Extend Output

Add Google Drive upload, YouTube publish, or database logging nodes for a complete content pipeline.

💡 How It Works

Trigger – Receives chat input (keyword or brief).
Prompt Expansion – GPT-5 turns it into a cinematic, Veo-3-optimized description.
Video Creation – Sends prompt + image to Veo-3 image-to-video.
Polling – Checks generation status every 30 seconds until complete.
Result – Returns direct video URL, ready for your next steps.