WTN SuiteWTN Suite

Quick Start Tutorial

Create your first narrated webtoon video in about 15 minutes

Quick Start Tutorial

This guide walks you through creating your first narrated webtoon video from start to finish. By the end, you'll have a fully narrated video ready to upload.

What you'll need:

  • WTN Suite installed (download here)
  • An AI API key (Google AI or OpenAI — free tiers available; Anthropic also supported)
  • A webtoon you want to narrate
  • About 15–20 minutes

Screenshot: Finished video output from WTN Suite

The Workflow at a Glance

WTN Suite's pipeline: Download → Crop into Pages → Load & Analyze → Generate Audio → Create Video. Two image types matter here — pages (from Webtoon Cropper, text bubbles intact, used by the AI to write narration) and panels (clean, text-free crops made automatically for your final video). Let's walk through the full process.

1

Download a Webtoon Chapter

Open WT-Downloader from the toolbar and paste a webtoon URL (e.g., https://www.webtoons.com/en/...). Choose your output folder and click Download.

The tool downloads all page images and organizes them automatically into numbered files.

Screenshot: WT-Downloader with a URL pasted and ready to download

2

Crop Your Chapter into Pages

Open Webtoon Cropper from the toolbar and load the scroll images you just downloaded. This step is required — WTN Suite can't work with the raw continuous scroll directly.

Click to place horizontal cut lines at natural scene breaks, then click Export. This produces individual pages, each still containing its text bubbles and dialogue — that's intentional, since the AI needs to read the dialogue to write accurate narration.

Screenshot: Webtoon Cropper with cut lines placed on a scroll image

💡 Tip

See the full Webtoon Cropper guide for tips on placing cuts well — where you cut affects narration quality later.

:::

3

Set Up Your AI Key (First Time Only)

Go to Settings (gear icon) and enter your API key:

You only need one. Google AI has a generous free tier, making it a great place to start.

Google AI
OpenAI
Anthropic

💡 Tip

Google AI's free tier gives you enough API calls to process several chapters per day at no cost.

:::

4

Load Your Pages

Click "Load Chapter & Review Panels" on the main toolbar. Select the pages you exported from Webtoon Cropper in Step 2 — not the original raw scroll images.

This just loads your pages into the main grid — no AI runs yet.

Screenshot: Main window showing loaded pages in the 6-column grid

ℹ️ Info

Auto Character Handling is built in — the AI will automatically detect and track characters when you run the analysis in the next step. No manual character setup required.

:::

5

Run the AI Pipeline

Click "Analyze & Narrate". This one click triggers everything else, and two things happen together in this same window:

  1. Automatic panel cropping — WTN Suite crops each page down into a clean, text-free panel. This runs differently depending on your content (webtoon-style vertical scroll vs. manga-style page layout — configurable in Settings). This clean panel is what ends up in your final video.
  2. Scene Analysis + Narrative Writing — The AI reads each page (dialogue and text bubbles included) to identify what's happening, then writes a continuous narration script across the whole chapter. It needs the page's text for this — a clean panel alone wouldn't give it enough context.

A progress bar shows the status. A typical 30–40 page chapter takes about 3–5 minutes.

Screenshot: Progress bar showing AI pipeline running

💡 Tip

You can review and edit any narrative text after processing. Click "Edit" next to any row's narration to make changes. If an automatic panel crop looks off on a specific page, click into it to adjust the crop boundaries manually.

:::

6

Generate Audio Narration

First, export your narration from the pipeline: click "Export Narration" in the main window. This saves a TXT file with one narration line per panel.

Then open Edge-TTS from the toolbar and switch to the Batch Generate tab — this creates one audio clip per panel automatically.

  1. Click 📁 Select .txt and choose the narration file you just exported
  2. Click 📂 Browse... and choose an output folder for the audio clips
  3. Choose a language and voice in the header
  4. Click ⚡ Generate Batch Audio

Edge-TTS generates one MP3 file per panel, numbered in order (narration_0001.mp3, narration_0002.mp3, ...). These numbered files are what the Video Compositor uses to match audio to panels.

Screenshot: Edge-TTS Batch Generate tab with progress bar

ℹ️ Info

Single Generate vs Batch Generate: The Single Generate tab creates one audio file from whatever text you type — useful for testing voices. The Batch Generate tab is what you need for video production: it reads your exported narration file and creates one audio clip per line.

:::

7

Create Your Video

Open the Video Compositor and:

  1. Load Image Folder — point to the clean panels (not the pages) exported in Step 5
  2. Load Audio Folder — point to the audio files from Step 6
  3. Choose your settings (resolution, aspect ratio)
  4. Click Generate Video

Your narrated video is saved as an MP4 file, ready to upload to YouTube, TikTok, or any platform.

Screenshot: Video Compositor with settings configured

You're Done!

You've just created a narrated webtoon video. From here, you can:

  • Better audio — Try Kokoro-TTS for higher-quality neural voices (Standard/Pro plans)
  • Polish scripts — Use the Script Rewriter for more cinematic narration (Pro plan)
  • Advanced editing — Export to CapCut Director for animations and subtitles
  • Precise character names — Use the Character Builder to assign exact names to auto-detected characters

Troubleshooting Your First Run

⚠️ Warning

Automatic panel crop looks off? Make sure your Webtoon Cropper cuts landed on clean scene breaks — a bad cut (e.g., mid-panel or mid-dialogue) can throw off the automatic panel crop during Analyze & Narrate. You can also click into any row in the grid to manually adjust its crop boundaries.

⚠️ Warning

API error? Double-check your API key in Settings. Make sure you've selected the correct AI provider (Google, OpenAI, or Anthropic) and that your key is active.

⚠️ Warning

Audio sounds wrong? Experiment with different voices in Edge-TTS. Adjusting the speech rate (try 1.0x–1.2x) can also improve results.

Next Steps