Upload documents and ask questions
Transcribe audio and generate responses based on prompts
Convert text to speech with adjustable rate and pitch
Remove background from images
OmniGen2: Unified Image Understanding and Generation.
NotebookLM conversational speech model
Generate audio from text with adjustable speed
nanonets ocr / smoldocling / monkey ocr / typhoon ocr
Clone a voice to speak any text
It's almost lovable...
Expressive Zeroshot TTS
Convert spoken words into text
Generate Gradio app code from user requests