Xybrid
SDKs

iOS

Native iOS SDK for on-device ML inference

The iOS SDK provides native Swift bindings to the Xybrid runtime for iOS and macOS applications.

Coming Soon - The iOS SDK is currently in development. In the meantime, you can use the Flutter SDK for cross-platform iOS development.

Planned Features

  • Native Swift API
  • SwiftUI integration
  • CoreML acceleration
  • Metal GPU support
  • Neural Engine (ANE) optimization

Expected API

Based on the Flutter SDK patterns, the iOS SDK will follow a similar structure:

import Xybrid

// Initialize
try await Xybrid.initialize()

// Load model from registry
let model = try await Xybrid.model(
    modelId: "whisper-tiny-candle",
    version: "1.0",
    registry: "https://registry.xybrid.dev"
).load()

// Run inference
let envelope = Envelope.audio(data: audioData)
let result = try await model.run(envelope: envelope)
print("Transcription: \(result.text)")

// Cleanup
model.unload()

Pipeline Example

let pipeline = try await Xybrid.pipeline(yaml: """
name: voice-assistant
stages:
  - whisper-tiny-candle@1.0
  - target: integration
    provider: openai
    model: gpt-4o-mini
  - kokoro-82m@0.1
""").load()

let result = try await pipeline.run(
    envelope: .audio(data: audioData)
)

// Play TTS response
let audioOutput = result.audio

Stay Updated

Follow the GitHub repository for iOS SDK announcements.

On this page