Generate faceless video scripts from a topic with Gemini or Claude Haiku

by Faceless Channel OS ✓ · 344 views · created 2026-07-23 · Content Creation, Multimodal AI

What this workflow does

This workflow has 7 nodes and runs when someone submits an n8n form (“Topic to faceless video script (JSON)”). It uses only n8n's built-in nodes. It also calls generativelanguage.googleapis.com and api.anthropic.com over HTTP.

How it runs

Trigger: When someone submits an n8n form (“Topic to faceless video script (JSON)”).

1. Set language and word budget (Code): runs custom JavaScript code
2. Route to the chosen model (Switch): routes items into 2 branches
3. Generate script (Gemini, free tier) (HTTP Request): calls generativelanguage.googleapis.com (POST)
4. Generate script (Claude Haiku) (HTTP Request): calls api.anthropic.com (POST)
5. Parse the script JSON (Code): runs custom JavaScript code
6. Split into individual scenes (Split Out): splits a list into separate items

HTTP calls to: generativelanguage.googleapis.com, api.anthropic.com

Before you upgrade to n8n 3.0

Nodes used (5)

• n8n Form Triggern8n-nodes-base.formTrigger
• Coden8n-nodes-base.code
• Switchn8n-nodes-base.switch
• HTTP Requestn8n-nodes-base.httpRequest
• Split Outn8n-nodes-base.splitOut

From the author

Quick overview This workflow collects a topic and settings via an n8n form, generates a short scene-by-scene faceless video script using either Google Gemini or Anthropic Claude Haiku, then normalizes the model output into a consistent JSON structure and…

View the original on n8n.io → Check your own copy