State-of-the-art image generation, in your browser. Bonsai Image 4B is a compressed text-to-image model from PrismML, built for local generation on iPhone, Mac, and GPUs.

• #Recommand
• #Text to Image

Detect and label objects in images and videos. LocateAnything is an NVIDIA vision-language model that finds objects, text, GUI elements, and points in images with natural language prompts.

• #Recommand
• #Vision-Language

Whisper AI is OpenAI’s speech recognition model for transcribing, translating, and understanding spoken audio.

• #Voice to Text

DeepSeek OCR 2 is an open-source OCR and document understanding model built for complex layouts, Markdown output, and human-like reading order.

• #Document OCR
• #Document to Markdown
• #Image to Text

DeepSeek OCR is an open-source vision-language OCR model that converts document images into structured text and Markdown with efficient visual token compression.

• #Document OCR
• #Document to Markdown
• #Image to Text

Sci Bot is an AI-powered research assistant connected with Sci-Hub. It lets users ask scientific questions in natural language, then tries to answer with information drawn from research papers.

• #ChatBot
• #Research

LTX-2 is an open-source AI video model that generates synchronized video and audio for creative, research, and production workflows.

VoxCPM is an open-source TTS model family for multilingual speech generation, voice design, and realistic voice cloning.

• #Text to Speech

Breakthrough in Emotionally Expressive and Duration-Controlled Auto-Regressive Zero-Shot Text-to-Speech