Ovis2.5 9B
High-accuracy vision & reasoning for complex tasks
Create and enrich datasets using AI and web search
Generates a podcast about today's top trending paper.
Ask questions about your webcam view and get text answers
Generate a podcast to discuss the topic of your choice!
Generate realistic speech and sounds from typed text
Generate speech audio from text with custom voice settings
Conversational speech generation
Upgraded to v1.0!
Detect, segment, classify objects in images and videos
Detect objects in images or videos
Object Detection & Scene Understanding for Images and Video
Describe any selected part of an image
Generate realistic dialogue from a script, using Dia!