GEDX402 Media

Synthesize English voice reply — POST text; returns audio bytes billed by character count. Voice-agent output leg after

Detect objects in an image with Detr Resnet 50 (@cf/facebook/detr-resnet-50). POST base64 image; returns bounding boxes

Describe or answer questions about an image with Llama 3.2 11B Vision Instruct (@cf/meta/llama-3.2-11b-vision-instruct).

Run safety moderation with Llama Guard 3 8B (@cf/meta/llama-guard-3-8b). POST messages or content to classify policy vio

Transcribe speech to text with Whisper (@cf/openai/whisper). POST audio (base64) or audio URL; returns transcript text b