> For clean Markdown of any page, append .md to the page URL. > For a complete documentation index, see https://fastpix.com/docs/llms.txt. > For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://fastpix.com/docs/_mcp/server. # Advanced Moderation overview Advanced Moderation is AI content moderation for video: it uses AI to review your video and audio for sensitive moments and act on them automatically, so your content complies with your platform's guidelines, community standards, and legal requirements. It finds sensitive moments in both the picture and the sound and can blur the video, beep or mute the audio, cut the moment out, or just flag it, producing a moderated copy of your video alongside the original so you can publish the clean version. Unlike basic [content moderation](/docs/in-video-ai/detect-nsfw-content-and-profanity), which detects and flags sensitive content for you to act on, Advanced Moderation acts on the flagged moments for you and returns a ready-to-publish, moderated video. \ ## How it works You use Advanced Moderation in two steps, both from the dashboard under **AI Agents > Moderation Agent**: 1. **[Create a rule](/docs/in-video-ai/create-a-moderation-rule).** A rule tells the AI what to look for in the video and audio, how strict to be (a threshold per condition), and what to do when it finds a match (blur, beep, mute, cut, or flag). You make a rule once and reuse it. 2. **[Run a job](/docs/in-video-ai/run-a-moderation-job).** A job applies a rule to the videos you choose, by media ID or by tags. Then you [review the moderated media](/docs/in-video-ai/review-moderated-media): a side-by-side of the source and moderated video, a timeline of every flagged moment, and a table of detections with their category, risk score, and action. \ ## What it can detect Advanced Moderation checks two kinds of content: * **Video:** violence, graphic violence, nudity, minors present, drugs and alcohol, smoking and tobacco, sexual content involving minors, child abuse, religious-sensitive content, and religious desecration. * **Audio:** profanity, harassment, threats, sexual content involving minors, child abuse, religious-sensitive content, and religious desecration. For each condition you set a threshold (0.1 to 1.0) that controls how readily a moment is flagged, and an action to take when it is. \ ## What it can do to a flagged moment * **Blur** the picture while the flagged moment is on screen. * **Beep** over flagged words or sounds in the audio. * **Mute** the audio while the flagged moment plays. * **Cut** the flagged moment out of the video. * **Flag** the moment in the results without changing the video. \ ## Common use cases * **User-generated content:** screen uploads on a social, marketplace, or community app, and automatically blur nudity or graphic violence and beep profanity before content goes live. * **Brand-safe and ad-supported video:** make sure videos meet advertising standards by flagging or removing violence, nudity, and profanity before you monetize them. * **Family-safe and kids' libraries:** build a clean catalog by cutting or flagging nudity, violence, and drug or alcohol content. * **OTT and broadcast compliance:** prepare edited cuts for different regions or airlines by bleeping profanity and blurring graphic footage. * **E-learning and corporate training:** keep training and course libraries free of inappropriate language or imagery. * **News and media:** mute or beep sensitive audio and blur graphic footage before publishing. \ #### Frequently asked questions Video content moderation is the process of reviewing, filtering, and acting on video and audio, whether pre-recorded or live, so it complies with your platform's guidelines, community standards, and legal requirements. FastPix Advanced Moderation does this automatically and can blur, beep, mute, cut, or flag the moments it finds. Advanced Moderation is a FastPix feature that automatically detects sensitive moments in a video's picture and sound and acts on them, blurring the video, beeping or muting the audio, cutting the moment out, or flagging it. It returns a moderated copy of the video alongside the original. Content moderation detects and flags sensitive content so you can decide what to do. Advanced Moderation goes further and acts on the flagged moments for you, producing a ready-to-publish moderated video. No. It creates a separate moderated copy and leaves your source video untouched, so you can compare the two and publish whichever you need. Yes. A single rule can detect and act on both video conditions (such as violence or nudity) and audio conditions (such as profanity or threats). UGC moderation is the process of checking videos uploaded by your users for sensitive content before they go live. With Advanced Moderation you create a rule once, then run it on uploads to automatically blur, beep, mute, cut, or flag anything that breaks your policy. Automated content moderation uses AI to detect and act on sensitive content without a person reviewing every video. FastPix Advanced Moderation detects moments in the video and audio and applies the action you set in your rule, producing a moderated copy you can publish. \ ## What's next * [Create a moderation rule](/docs/in-video-ai/create-a-moderation-rule) to define what to detect and how to act on it. * [Run a moderation job](/docs/in-video-ai/run-a-moderation-job) to apply a rule to your videos. * [Review moderated media](/docs/in-video-ai/review-moderated-media) to see the results.