Cohere Multilingual ASR
Transcribe audio clips to text in multiple languages
Zero-shot expressive voice cloning and speech generation
Generate natural speech from custom voice samples
Granite 4.0 1B Speech recognition and translation demo
Demo of the Collection of Qwen Image Edit LoRAs
Lumian-VLR / VisionThink / MiniCPM-V / Typhoon-OCR / olmOCR
Edit videos with AI-driven prompts and optional reference images
Ultra fast universal speech enhancement model.
Fast high quality video with audio generation
Generate speech from text with voice design, cloning, or presets
Generate or edit images from text prompts
Edit images with AI using detailed text instructions
Decompose an image into editable layers
Add objects to images using text prompts
Create a face morphing video from images
Rewrite image prompts into detailed English descriptions
Convert any static image into a 3D Gaussian Splat scene