ZelAI SDK

Access ZelAI Cloud SDK for multimodal generation and analysis via REST and WebSocket.

Updated Jan 6, 2026
One-click install
npx skills add https://github.com/ZelStudio/zelai-cloud-sdk --skill zelai-sdk
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ZelAI SDK
Source: https://github.com/ZelStudio/zelai-cloud-sdk/tree/main
Command: npx skills add https://github.com/ZelStudio/zelai-cloud-sdk --skill zelai-sdk

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

The ZelAI SDK provides a single, developer-friendly interface to access ZelStudio's Cloud AI Generation API, enabling automated multimodal creation and analysis. It covers image generation, video creation, LLM text generation, STT transcription, TTS speech synthesis, CDN downloads, and an OpenAI-compatible API, all through REST and WebSocket endpoints.

Core Features & Use Cases

  • Image generation, editing, upscaling, and dual-image editing for production workflows, marketing assets, and creative exploration.
  • Video creation from static images with motion prompts and CDN delivery for tutorials, campaigns, and social media content.
  • LLM text generation with memory, streaming, and JSON output to power chatbots, assistants, and content pipelines.
  • STT and TTS for voice-enabled apps, plus CDN operations to fetch and transform generated media.
  • OpenAI-compatible API to blend ZelAI capabilities into existing OpenAI-based tooling.

Use cases span accelerated product design, rapid prototyping, marketing asset production, and knowledge-work automation.

Quick Start

Install the ZelAI SDK via npm and create a client with your API key. Then call generateImage, generateVideo, or generateText to begin.

Frequently Asked Questions about ZelAI SDK

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate images and text using a multimodal AI SDK?

To generate images and text using a multimodal AI SDK, install the package via npm and instantiate a client with your API key to call REST or WebSocket endpoints for image, video, and LLM text generation.

Can I use an OpenAI-compatible API for text generation and chatbots?

Yes, you can use an OpenAI-compatible API for text generation and chatbots. The SDK provides a compatible interface alongside native REST and WebSocket endpoints to blend capabilities into existing OpenAI-based tooling.

Does the SDK support speech-to-text transcription and text-to-speech synthesis?

Yes, the SDK fully supports speech-to-text transcription and text-to-speech synthesis. It provides dedicated endpoints to integrate voice recognition and audio generation into voice-enabled applications.

What is the best way to automate video creation from static images?

The best way to automate video creation from static images is to use the SDK's video generation endpoints with motion prompts. The resulting media is delivered via CDN for use in tutorials or social campaigns.

Do I need additional services or external dependencies to run this TypeScript SDK?

No, you do not need additional services or external dependencies to run this TypeScript SDK. It operates entirely using standard npm-based tooling, requiring only your validated API keys to ensure safe, scalable usage.

How are API rate limits reported when scaling multimodal generation workflows?

API rate limits are reported directly by the SDK when scaling multimodal generation workflows. It validates API keys and exposes rate limit metrics to ensure safe, scalable usage across image, video, and text processing.