Create and run Jupyter notebooks interactively

Enhance and colorize old photos

Generate music from text prompts

AI Generated Image & Deepfake Detector

Lunch web-based text-to-speech interface

Generate React TypeScript App

Talk to a language model

Track points in a video

Vocal and background audio separator

FitDiT is a high-fidelity virtual try-on model.

Search and save datasets generated with a LLM in real time

✨[With v1.0.0] Accelerated TTS on Kokoro-82M

Convert voice to match another using reference audio

Generate Talking avatars from Text-to-Speech

MaskGCT TTS Demo

Generate captions for images in various styles

Transform your voice into a singer's

Generate text by combining an image and a question

Languages ru,en,zh-cn,ja,de,fr,it,pt,pl,tr,ko,nl,cs,ar,es,hu

Transcribe audio to text with speaker diarization