F5-TTS
🗣
2.93k
F5-TTS & E2-TTS: Zero-Shot Voice Cloning (Unofficial Demo)
Generate Talking avatars from Text-to-Speech
Clone a voice to read your custom text
Nanonets / olmOCR / RolmOCR / Aya-Vision / Qwen2-VL-OCR
Generate captivating stories from images
Generate animated videos from images and motion sequences
install PolaroidVL Model locally on your devices
Create your own AI comic with a single prompt