text.generate_description

Operation: text.generate_description
Category: ai
Tags: ai, youtube, description, seo, text

Generate an SEO-optimized YouTube description with chapters and hashtags

Runtime

Type: AI Provider (routed via provider registry)
Timeout: 300s
Retries: 3 (ExponentialWithJitter)

Inputs

Name	Type	Required	Default	Description
transcript	String	Yes	—	Full transcript text
title	String	No	—	Video title (for SEO alignment)
chapters	JSON	No	—	Array of {timestamp, title} chapter markers

Outputs

Name	Type	Description
description	String	Full YouTube description text
hashtags	JSON	Array of recommended hashtags
chapter_markers	String	Formatted chapter timestamps for description

Default Configuration

{
  "include_chapters": true,
  "max_length": 5000,
  "modality": "text",
  "provider": "gemini"
}

Usage

TypeScript

import { WorkflowBuilder } from "@fabric-platform/sdk";

const workflow = new WorkflowBuilder("my-workflow")
  .node("text-generate-description", "ai_invoke", (n) =>
    n.config({
      operation: "text.generate_description",
      // ... node-specific config
    })
  )
  .build();

Python

from fabric_platform import FabricClient

fabric = FabricClient(api_key="fab_xxx")

wf_id = fabric.upsert_workflow("my-workflow", nodes=[
    {
        "key": "text-generate-description",
        "kind": "ai_invoke",
    },
])

Rust

use fabric_sdk::FabricClient;

let client = FabricClient::new("http://localhost:3001", api_key)?;

let wf_id = client.upsert_workflow("my-workflow", serde_json::json!({
    "nodes": [{
        "key": "text-generate-description",
        "kind": "ai_invoke"
    }]
})).await?;

curl

curl -X POST http://localhost:3001/v1/workflow-definitions \
  -H "Authorization: Bearer $FABRIC_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "name": "my-workflow",
    "nodes": [{
      "key": "text-generate-description",
      "kind": "ai_invoke"
    }]
  }'