For AI agents: a documentation index is available at the root level at /llms.txt and /llms-full.txt. Append /llms.txt to any URL for a page-level index, or .md for the markdown version of any page.
StatusSupportDiscussionsLog inSign Up
Docs HomeAPI ReferenceVideo on DemandAI FeaturesLive StreamingVideo PlayerVideo DataCloud PlayoutRecipes
Docs HomeAPI ReferenceVideo on DemandAI FeaturesLive StreamingVideo PlayerVideo DataCloud PlayoutRecipes
  • Get started
    • Overview
  • Video intelligence
    • Detect NSFW content and profanity
    • Extract named entities from a video
    • Generate video chapters
    • Generate a video summary
  • AI Agents
    • Notes Agent
  • AI events
    • In-video AI events
LogoLogo
StatusSupportDiscussionsLog inSign Up
On this page
  • What you can do
  • How it works
  • Get started
Get started

Overview

Analyze, moderate, and enrich your videos with built-in AI

Was this page helpful?

Detect NSFW content and profanity

Learn how to use FastPix to detect NSFW and profane content in video or audio using confidence scores and the moderation API.
Next
Built with

FastPix In-Video AI runs directly on your uploaded media — no external services, no extra infrastructure. Every AI feature works through the same API you already use to upload and transform videos.

What you can do

Moderate content automatically. Flag NSFW frames and detect profanity in audio before your content reaches viewers. FastPix scans video and audio tracks separately and returns timestamped results you can act on programmatically.

Extract structured data from video. Pull named entities (people, places, organizations, brands) mentioned in your video’s audio track. Use the output to build search indexes, auto-tag content, or feed recommendation systems.

Generate chapters and summaries. Let FastPix break a long video into logical chapters with titles and timestamps, or produce a text summary of the entire video. Both features use the audio transcript combined with visual scene analysis.

How it works

AI features are applied as part of the video processing pipeline. When you create or update a media asset, include the relevant AI parameters in your API request. Results are delivered via webhooks once processing completes — the same webhook pattern you use for transcoding status.

Each feature produces structured JSON output attached to your media asset, accessible through the API or visible in your dashboard.

Get started

Detect NSFW content and profanity

Flag inappropriate visual and audio content automatically.

Extract named entities from a video

Identify people, places, and organizations mentioned in your video.

Generate video chapters automatically

Break long videos into titled, timestamped sections.

Generate a video summary

Produce a text summary of your video content.