An AI Agent to Create Faceless YouTube Videos

Go to Workflow
0 views
Built by simonscrapes simonscrapes
Created on June 07, 2026

Description

Runthrough
Video runthrough

Use Case
Create YouTube videos without on-camera presence:

You want to generate passive content
You need scalable video production
You want to automate content creation
You need consistent video output

What this Workflow Does
The workflow automates video production:
Generates audio narration
Creates complementary stock imagery and turns static images into motion
Syncs audio and visual elements
Produces ready-to-upload YouTube content

Setup
Configure text-to-speech audio generation
Set up AI image generation service
Connect Shotstack API for video composition
Define content parameters and themes

How to Adjust it to Your Needs
Modify audio generation parameters
Customize image styles
Adjust video composition

Tools (requires API access & some are paid for tools)
Elevenlabs for audio generation
Leonardo for image generation and motion images (can be swapped out)
Shotstack for syncing image to video
OpenAI Whisper for transcription

Cost of production
Around $0.80 per video at time of writing

Nodes Used (6)

Auto-fixing Output Parser
@n8n/n8n-nodes-langchain.outputParserAutofixing
Basic LLM Chain
@n8n/n8n-nodes-langchain.chainLlm
Google Drive
n8n-nodes-base.googleDrive
HTTP Request
n8n-nodes-base.httpRequest
OpenAI Chat Model
@n8n/n8n-nodes-langchain.lmChatOpenAi
Structured Output Parser
@n8n/n8n-nodes-langchain.outputParserStructured