Chat with AI

Powered by Ollama local models

Start a conversation...

Text to Speech

XTTS-v2 — Multi-language voice synthesis

Generating speech...

Speech to Text

Faster-Whisper Large-v3 — Accurate speech recognition

Record Audio
Click to start recording
Or Upload Audio File
🎤

Drop audio file here or click to browse

Transcribing audio...

Object Detection

YOLOv11x — Real-time object detection

📷

Drop an image here or click to browse

0.25
Detecting objects...

Vision AI

Florence-2 — Image captioning, OCR, and more

👁

Drop an image here or click to browse

Task
Caption
Detailed Caption
Very Detailed
OCR
Object Detection
Region Captions
Analyzing image...

Image Generation

FLUX.1 Dev — via ComfyUI (must be running on port 8188)

Generating image... (this may take 30-60s)
🎨