verging-ai

Extract descriptions, objects, and text from images using AI vision capabilities. This skill provides a simple API integration for GPT-4o Vision through verging.ai.

Developers need a simple way to add voice output to their applications without managing complex audio infrastructure. This skill provides direct access to OpenAI's TTS-1-HD model through a straightforward API call.

Converting audio recordings to text manually is slow and error-prone. This skill provides a simple API to transcribe audio files using OpenAI Whisper, returning accurate text in seconds.

Creating images with AI requires managing API keys, request parameters, and response handling. This skill provides a ready-to-use interface to generate images through the verging.ai proxy API, supporting both standard and HD quality modes.

Users need a simple way to call GPT-4o through the verging.ai proxy. This skill provides ready-to-use curl examples for both streaming and non-streaming chat completions.