Docs / Protection / Ai Moderation

AI Moderation for Telegram Groups (Automatic Content Detection)

OmniGest uses artificial intelligence (OpenAI) to automatically detect and remove inappropriate content from your Telegram group — spam, hate speech, NSFW, and scam messages.

What does it detect?

Category Description Action
CSAM (minors) Child sexual abuse material Permanent ban (not configurable)
NSFW Explicit sexual content Configurable
Scam/Phishing Scams, fake investments Configurable
Violence Graphic violent content Configurable
Harassment Threats, harassment Configurable
Self-harm Self-harm content Configurable

How does it work?

  1. The user sends a message (text or photo)
  2. The message is delivered normally (without delay)
  3. In the background, the AI analyses the content
  4. If prohibited content is detected: the message is deleted and the action is triggered

Important: The analysis is asynchronous — the message may be visible for 1-2 seconds before being deleted.

Configuration

  1. /config → Select group → 🤖 AI Moderation
  2. Enable/Disable — Toggle on/off
  3. Action — For non-CSAM categories: delete, warn, mute, kick, ban

Zero tolerance for CSAM

CSAM detection (child sexual abuse material) has a very low threshold and always results in a permanent ban. This action is NOT configurable — it is a mandatory security measure.

Notes

  • Administrators are exempt
  • Analyses text and images (photos)
  • Does not analyse videos, GIFs or stickers
  • If the AI is unavailable, messages pass normally (fail-open)
  • Admins receive a private notification when the AI takes action

Frequently Asked Questions

How does OmniGest's AI moderation detect spam?

OmniGest sends suspicious messages to OpenAI's API for analysis. The AI classifies content into categories (spam, hate speech, NSFW, scam) and takes the configured action automatically.

Is AI moderation free in OmniGest?

Yes. AI moderation is included in the free plan. OmniGest covers the OpenAI API costs — there are no hidden charges.

Can AI moderation detect content in languages other than English?

Yes. OpenAI's models support multilingual content detection including Spanish, Portuguese, Russian, Arabic, and many more languages commonly used in Telegram groups.