KaniTTS2-en
Generate speech from text with custom voice options
SOTA real-time object detection model
Large Animatable Human Model
Generate audio responses from text or audio
Convert images and videos into dotted patterns
Upgraded to v1.0!
Generate app code from your idea
Generate a virtual try‑on image of a person wearing a garment
Generate 3D scenes from images with prompts
Generate synchronized audio from video or text prompts