Build document scanning, image processing, facial authentication, desktop automation, and browser video workflows with focused guides for developers, integrators, product teams, marketers, and creators.
Choose your path
Code-led API guides include request examples, response handling, troubleshooting, privacy notes, and practical production guidance.
Latest tutorials
Each tutorial focuses on a defined result, from a working API request to a finished browser-based project. Choose a guide and follow it at your own pace.
Working examples for document and image processing endpoints.
Send an ID document by URL or direct upload, read normalized fields and MRZ data, and handle the structured JSON response safely.
Read the DOCSCAN tutorial →
Upload local files or process public image URLs, decode transparent output, and use bounded concurrency for larger image collections.
Read the background removal tutorial →
Remove captions, labels, timestamps, and watermarks you are authorized to remove, then consume or display the cleaned output.
Read the TXT-REMOVE tutorial →Step-by-step guidance for facial authentication, desktop automation, and browser media production.
Start with a bounded task, use writing, OCR, document, and recording tools, then add reusable Skills or MCP integrations when the workflow needs them.
Read the Think-Act tutorial →
Add optional face enrollment and returning-user authentication, then connect the result to your existing account and session flow.
Read the FACEIO tutorial →
Create a project, import and trim clips, add text or subtitles, resize for common social formats, and export the finished video in your browser.
Read the video editor tutorial →Build with PixLab
Browse the API endpoint directory for complete references, or open the PixLab Console to create an API key and test the document and image processing examples with your own inputs.