PixLab Machine Vision & Media Processing APIs

What is PixLab?

PixLab offers a comprehensive suite of Machine Vision and Media Processing APIs designed for developers. It provides a unified platform allowing seamless integration of intelligent features into applications using state-of-the-art deep learning models. The service simplifies tasks such as analyzing images and videos for content moderation, recognizing objects, blurring faces, and scanning various documents including passports and ID cards. PixLab supports integration through standard HTTP requests, making it compatible with numerous programming languages like Python, PHP, JavaScript, Ruby, and Java.

Beyond analysis, PixLab delivers extensive media processing capabilities. Developers can utilize its APIs to transform and filter images and videos with effects like resizing, cropping, adding text overlays, and adjusting colors. The platform also includes robust media storage options, featuring high availability, global CDN delivery over SSL, and the ability to proxy directly to a user's AWS S3 bucket for enhanced control over assets. This combination of vision analysis, media manipulation, and storage makes it a versatile tool for building smarter applications.

Features

Face Detection & Blurring: Detect human faces in images/videos and apply blur filters.
Document Scanning (DOCSCAN): Scan and extract data from over 11,000 types of ID documents across 197+ countries.
Content Moderation (NSFW): Analyze images for Not Safe for Work content and return a confidence score.
Image Tagging (TAGIMG): Generate human-readable descriptions and tags for image content using neural networks.
Media Processing APIs: Process, transform, and filter images/videos (resize, crop, blur, draw text, merge, etc.).
Media Storage: Offers highly available storage with global CDN and optional AWS S3 bucket proxy.
Dynamic Image Generation: Create new images programmatically and draw text or shapes.
Unified API Platform: Access over 130 machine vision and media processing endpoints.

Use Cases

Implementing eKYC (Know Your Customer) processes.
Automating content moderation for user-generated media.
Anonymizing images and videos by blurring faces.
Generating dynamic image-based challenges (e.g., CAPTCHAs).
Automatically tagging visual assets for organization and search.
Integrating image/video editing capabilities into applications.
Building applications requiring facial analysis.
Extracting text and data from documents via OCR.

FAQs

What happens if I exceed my monthly API call quota?

You'll be charged $0.9 per 1000 additional requests (media processing requests are free for the Enterprise plan after the quota). You will be notified by email when you reach 90% of your monthly quota.
What happens if I exceed my storage quota?

You can upgrade your plan or connect your AWS S3 bucket to be used as the primary data store. Otherwise, the oldest files may be erased first to free up space for new files.
Why are there no free plans?

PixLab focuses on providing high-quality services which require significant computing resources. A 7-day free trial is offered to test the API before committing to a plan.
What are the limits during the free trial period?

The 7-day trial period has a limit of 500-1000 analysis calls. Exceeding this may lead to charges unless the trial is explicitly cancelled. Abuse of the offer may lead to cancellation.
How can I cancel my subscription?

Submit a subscription cancellation request via the support tab in your dashboard. Cancellations are typically processed within 72 hours. No refunds are issued for unused services.
Where are my media assets stored?

By default, assets are stored on the pixlab.xyz storage cluster. However, if you connect your own AWS S3 bucket via the PixLab Console, assets are stored only on your S3 bucket.