PDF to Video Example

Overview

PDF to Video extracts the text of a PDF, turns it into a narration split into scenes, reads it with a voice and puts a visual under each scene. PDF to Brainrot does the same over a gameplay clip. Send the PDF as a public https:// link in pdfUrl (up to 20 MB; Hooked downloads it) or as the file itself in pdfBase64 (up to 10 MB). The PDF needs a text layer: a scanned or image-only PDF answers 400 before anything is charged. summaryType, targetDuration and customPrompt work as in Article to Video.

The create call downloads the PDF and checks its text, then answers in a few seconds with the projectId and status processing. The scenes are written after that, then the video is generated and rendered. If the scenes cannot be written, the project becomes failed (the reason is in message), the credits come back and your webhook gets the failure.

From a link

const response = await fetch('https://api.hooked.so/v1/project/create/pdf-to-video', {
  method: 'POST',
  headers: {
    'x-api-key': process.env.HOOKED_API_KEY,
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    pdfUrl: 'https://example.com/reports/annual-report-2025.pdf',
    voiceId: '1000',
    summaryType: 'summarize',
    targetDuration: 60,
    customPrompt: 'Lead with the three biggest numbers',
    mediaType: 'ai-images',
    presetSettings: { preset: 'cinematic' },
    aspectRatio: 'ratio_9_16',
    caption: { preset: 'tiktok' },
    webhook: 'https://yoursite.com/hooked-webhook?token=YOUR_SECRET',
    metadata: { reportId: '2025-annual' }
  })
});

const { data } = await response.json();
console.log('Project ID:', data.projectId); // status: "processing"

From a file on disk

import { readFileSync } from 'node:fs';

const body = {
  pdfBase64: readFileSync('./employee-handbook.pdf').toString('base64'),
  pdfFileName: 'employee-handbook.pdf',
  voiceId: '1000',
  summaryType: 'key_as_is',
  mediaType: 'ai-images',
  webhook: 'https://yoursite.com/hooked-webhook?token=YOUR_SECRET'
};

const response = await fetch('https://api.hooked.so/v1/project/create/pdf-to-video', {
  method: 'POST',
  headers: {
    'x-api-key': process.env.HOOKED_API_KEY,
    'Content-Type': 'application/json'
  },
  body: JSON.stringify(body)
});

Files over 10 MB go through pdfUrl: put the file somewhere public (a signed link of your own storage works) and send the link.

Study notes over gameplay

import os
import requests

response = requests.post(
    "https://api.hooked.so/v1/project/create/pdf-to-brainrot",
    headers={"x-api-key": os.environ["HOOKED_API_KEY"]},
    json={
        "pdfUrl": "https://example.com/notes/biology-chapter-3.pdf",
        "voiceId": "1000",
        "summaryType": "summarize",
        "targetDuration": 60,
        "gameplaySettings": {"selectedGame": "subway-s", "selectedVideo": "subway-s-3"},
        "caption": {"preset": "beast"},
        "webhook": "https://yoursite.com/hooked-webhook?token=YOUR_SECRET",
    },
)

print(response.json()["data"]["projectId"])

When the PDF is refused

Answer	What to do
`400 pdf: The PDF has no readable text …`	It is a scan or an image-only PDF: export it with OCR (a text layer) first.
`400 pdf: The PDF is password-protected …`	Send a copy without a password.
`400 pdfUrl: The PDF is larger than 20 MB` / `pdfBase64: The PDF is larger than 10 MB …`	Split the document, or compress its images.
`400 pdfUrl: The file at this URL is not a PDF`	The link answers an HTML page (a viewer or a login) instead of the file: use the direct download link.
`400 pdfUrl: Must be a public https URL (…)`	The host is private, local or redirects to one.

Nothing is charged for any of these.

Getting the video

Wait for the webhook or poll GET /v1/project/{projectId} until video.status is COMPLETED, then download video.url.

Send an Idempotency-Key header to retry safely: if a request times out or answers 5xx, sending it again with the same key and body returns the first answer instead of creating (and charging) the project twice.

Teams in bring-your-own-keys mode are not charged credits, but need OpenRouter and ElevenLabs in Settings → AI keys (and Gemini for the Omni Flash model). No Firecrawl key is needed: Hooked reads the PDF itself. A missing key answers 402 missing_credentials with the list in missingProviders, before anything is created.

See the PDF to Video and PDF to Brainrot references for every field and error.

Getting Started

Core Concepts

AI Agents

Guides

Examples

Overview

From a link

From a file on disk

Study notes over gameplay

When the PDF is refused

Getting the video

​Overview

​From a link

​From a file on disk

​Study notes over gameplay

​When the PDF is refused

​Getting the video

Overview

From a link

From a file on disk

Study notes over gameplay

When the PDF is refused

Getting the video