Hypereal TypeScript SDK
A typed Node.js client for Hypereal AI APIs: chat, responses, image generation, video generation, audio, jobs and storage.
pnpm add hypereal-sdkimport { Hypereal } from 'hypereal-sdk';
const client = new Hypereal({
apiKey: process.env.HYPEREAL_API_KEY!,
});
const image = await client.images.generate({
model: 'gemini-3-1-flash-t2i',
prompt: 'A cinematic portrait in neon light',
aspect_ratio: '16:9',
});One client for the API surface you already expose
The SDK wraps the stable `/api/v1` endpoints with small resource objects, consistent auth headers, timeout handling and structured API errors.
Models
List available LLM, image, video, audio and specialty models from one typed client.
Chat and Responses
Use OpenAI-compatible chat completions or the Responses API with streaming support.
Image Generation
Generate and edit images with Nano Banana, GPT Image, FLUX and other hosted models.
Video Generation
Create videos with typed request bodies, webhooks, async job polling and model routing.
Audio
Call text-to-speech, speech recognition, voice clone and music generation endpoints.
Storage
Create signed upload URLs, upload files directly, commit objects and manage visibility.
const completion = await client.chat.completions.create({
model: 'gpt-5.5',
messages: [
{ role: 'user', content: 'Draft a launch checklist.' },
],
});const object = await client.storage.uploadFile(file, {
filename: 'training-image.png',
contentType: 'image/png',
kind: 'dataset',
});Predictable method names, plain JSON underneath
Every SDK method maps directly to an HTTP endpoint, so debugging remains simple with curl, logs or API gateway traces.
client.models.list()/v1/modelsclient.chat.completions.create()/v1/chat/completionsclient.responses.create()/v1/responsesclient.images.generate()/v1/images/generateclient.videos.generate()/v1/videos/generateclient.audio.generate()/v1/audio/generateclient.jobs.poll()/v1/jobs/{id}client.storage.uploadFile()/v1/storage/upload