← Back to pipelines

Script Writer

Turn any topic into a complete video production blueprint, narration, visual plan per segment, audio direction, and a step-by-step shot list.

4

Still needed: Topic, Genre

Best for

  • •Planning a video from scratch, AI writes the script and plans every visual
  • •Automatically deciding which tools to use for each scene
  • •Creating narration scripts with natural pacing for voice generation
  • •Structuring multi-segment videos with consistent style

When to use

  • •Always start here when producing a full video from a topic
  • •When you want AI to plan the visuals, narration, and music for you

Tips

  • ✓The more detail you provide about the topic, the better the output
  • ✓Use the instructions field to set style preferences (e.g. cinematic, upbeat, educational)
  • ✓The output includes a visual diagram showing how all the pieces connect
  • ✓Each scene specifies which pipelines to use and in what order

Articles about this pipeline

Script Writer API

Call this pipeline from your own code. One request dispatches a run; the model is an input field, not a separate endpoint.

4 inputs
2 required
4 credits
bun add @pipe2-ai/sdk 
import { createClient } from "@pipe2-ai/sdk";

const client = createClient(process.env.PIPE2_TOKEN!);

const { run_pipeline } = await client.RunPipeline({
  pipeline_slug: "script-writer",
  input: {
    topic: "why sourdough starters actually work",
    genre: "documentary",
  },
});
pip install pipe2 
import asyncio
import os

from pipe2 import Pipe2Client

client = Pipe2Client(token=os.environ["PIPE2_TOKEN"])

run = asyncio.run(client.run_pipeline(
    pipeline_slug="script-writer",
    input={
        "topic": "why sourdough starters actually work",
        "genre": "documentary",
    },
))
go get github.com/pipe2-ai/sdk-go 
client := pipe2.NewClient(os.Getenv("PIPE2_TOKEN"))

input := json.RawMessage(`{
  "topic": "why sourdough starters actually work",
  "genre": "documentary"
}`)

run, err := pipe2.RunPipeline(context.Background(), client, "script-writer", input)
if err != nil {
    log.Fatal(err)
}
brew install pipe2-ai/tap/pipe2 
pipe2 pipelines run \
  --pipeline script-writer \
  --input-json '{"topic": "why sourdough starters actually work", "genre": "documentary"}' \
  --wait

Get an API token →

Parameters

genre required

Tone and format of the script — drives pacing, structure and voice.

documentaryeducationalexplainerpromocinematic default documentary
topic required

What is your video about?

string
duration_min

Target read time in minutes. The script is written to fit.

13510 default 1
Show all 4 inputs
instructions

Optional production guidance

string

Use it from an AI agent

Point any MCP client at pipe2 and your agent gets these tools. It finds this pipeline, reads the same schema above, then runs it.

  • list_pipelines
  • get_pipeline_schema
  • run_pipeline
  • get_pipeline_run_status
  • request_upload
https://mcp.pipe2.ai/mcp 
{
  "mcpServers": {
    "pipe2ai": {
      "url": "https://mcp.pipe2.ai/mcp",
      "headers": { "Authorization": "Bearer YOUR_TOKEN" }
    }
  }
}

Full API reference MCP setup CLI reference

Script Writer: AI Production Blueprint Generator

Enter a topic and get a complete production blueprint for a documentary video. AI acts as a film director, writing narration, designing visual strategy per segment, choosing which tools to use and why, planning audio, and outputting a visual workflow diagram.

How It Works

  1. Enter your topic: describe your documentary subject
  2. Choose duration: 1, 3, 5, or 10 minutes
  3. Set tone: educational (PBS style), dramatic (tense and evocative), or conversational (warm, approachable)
  4. Get your blueprint: AI designs the full production plan with a step-by-step plan per segment

What You Get

  • Narration script: complete sentences at 130 WPM, ready for Audio Generator
  • Visual strategy per segment: which tools to use (AI-generated, stock footage, or text card) and WHY
  • Tool steps: exact prompts, queries, and parameters for each step
  • Audio plan: voice, language, music mood, and duration
  • Assembly instructions: transition style, color grading, pacing notes for Video Reel
  • Workflow diagram: visual dependency graph of the entire production pipeline

Production Workflow

Script Writer is step 1. AI reads the blueprint and executes each step automatically: generating images, searching footage, applying motion, trimming clips, creating title cards, generating narration and music, then assembling everything in Video Reel.

Frequently Asked Questions

How many sections will my script have?
The number of sections scales with your chosen duration: 4-6 sections for 1 minute, 6-10 for 3 minutes, 8-12 for 5 minutes, and 12-18 for 10 minutes.
What is the narration word count?
Scripts are written at 130 words per minute, the standard documentary narration pace. A 10-minute script contains approximately 1,300 words across all sections.
Can I edit the script after generating it?
Yes, the output is plain JSON you can copy and edit. The structured format makes it easy to adjust individual sections without rewriting the whole script.
How do I use this with other tools?
Copy each section's narration into the Audio Generator for voiceover, the query from any visual_strategy step marked footage-search into Footage Search for b-roll, and each section's title into the Text Card tool for title cards.
How many credits does it cost?
4 credits per script. AI generates the full script in a single call, so the cost is fixed regardless of script length.

Explore more pipelines

See all →
Video Generator
from 9.5
Video Generator →
Image Generator
0.2-6.4
Image Generator →
Audio Generator
0.7-1.3
Audio Generator →
Music Generator
2.5-45.1
Music Generator →