omni-moderation

The omni-moderation model is a powerful tool for identifying potentially harmful content in text and images. It supports a 32768 token context window and can handle a wide range of inputs and outputs, including text, images, video, audio, transcription, and text-to-speech.

Supports a 32768 token context window. Handles Text, Image, Video, Audio, Transcription, Text-to-Speech inputs and outputs. Supports fine-tuning for custom applications.

This model is free to use and can be a valuable asset for content moderation and safety applications.