440
Leffa
π
Generate images with virtual try-on or pose transfer
Stream webcam video and detect objects in real-time
Convert spoken words to text and voice assistant responses
Blind vote on HF TTS models!
Fast, efficient, & multilingual text-to-speech
Generate 3D content from images or text
Realtime implementation of Whisper large turbo
On device model trained on completely open licenced data !
Run Python code in your browser
Personalised Podcasts For All - Available in 13 Languages