jigsawstack/vocr 📝❓🔢 → 📝

▶️ 20 runs 📅 Jun 2025 ⚙️ Cog 0.15.8
document-to-json image-to-text ocr

About

Recognise, describe and retrieve data within an image with great accuracy.

Example Output

Prompt:

"describe the image in detail"

Output

/tmp/tmp1l_d4mvw/vocr_result.json

Performance Metrics

17.57s Prediction Time
17.57s Total Time
All Input Parameters 
{
  "url": "https://media.snopes.com/2021/08/239918331_10228097135359041_3825446756894757753_n.jpg",
  "prompt": "describe the image in detail",
  "api_key": "sk_ba8d51db7829aef7ec445bb80dd59b7ff2c320d851eb6ae4cf41aacfab4df81c690774957983ebcc02f08429fccdfe42b4d8ee6a40b404399c10ca3bcabdbb72024KnIELzWIzzblw1gtM6"
}
Input Parameters
url Type: string
The image URL. Not required if file_store_key is specified.
prompt Default: Describe the image in detail.
The prompt used to describe the image. Can be a string or array of strings for specific data extraction. Default is 'Describe the image in detail.'
api_key Type: string
🔐 Your JigsawStack API Key (required)
page_range Type: array
Specifies a range of pages to process with VOCR, provided as a two-element array: [startPage, endPage]. For example, [1, 10] processes pages 1 through 10. The range must span 10 or fewer pages.
file_store_key Type: string
The key used to store the image on Jigsawstack File Storage. Not required if url is specified.
Output Schema

Output

Type: string

Version Details
Version ID
89fee97b435eed5a19f9e1a7279e48da91fe639483d82c941327b52972ce0503
Version Created
June 27, 2025
Run on Replicate →