Generate text based on prompts
Identify and describe human poses in images
Start a simulated robot arm animation
Generate speech from text using gTTS or Edge TTS
Detect objects in images with multiple models
Compare poses and get feedback
Display logs from a webhook trigger
Streamlit template space
Upload files and query knowledge base
Transcribe audio files to text with timestamps
Send camera images to analyze with text feedback
Build AI agents visually
Sample MCP server
Describe an image using text
Capture images with camera and get descriptions