> ## Documentation Index
> Fetch the complete documentation index at: https://docs.nexa.ai/llms.txt
> Use this file to discover all available pages before exploring further.
# Quickstart
> Get started with NexaSdk in minutes.
## **Installation**
The NexaSdk for iOS/macOS can be downloaded directly from the official distribution link below.
Download [NexaSdk.xcframework](https://nexa-model-hub-bucket.s3.us-west-1.amazonaws.com/public/ios/latest/NexaSdk.xcframework.zip)
### **Add Dependency**
In Xcode, download and drag [NexaSdk.xcframework](https://nexa-model-hub-bucket.s3.us-west-1.amazonaws.com/public/ios/latest/NexaSdk.xcframework.zip) into your Project/Workspace.
Make sure the framework is added to the target's Frameworks, Libraries, and Embedded Content and set to Embed & Sign if you need the framework bundled in the app.
## **Run Your First Model**
Create an ASR instance and load a model:
```swift theme={"dark"}
import Foundation
import NexaSdk
let asr = try Asr(plugin: .ane)
try await asr.load(from: "")
```
Use the loaded model to transcribe an audio file:
```swift theme={"dark"}
let asrResponse = try await asr.transcribe(options: .init(audioPath: ""))
print(asrResponse.asrResult.transcript)
```
**Load Model from HuggingFace**
You can download models from the HuggingFace using the official [Hub](https://github.com/huggingface/swift-transformers) library and load them via the `load(from:)` API. For example:
```swift theme={"dark"}
import Hub
import NexaSdk
let modelDir = try await Hub.snapshot(from: "NexaAI/parakeet-tdt-0.6b-v3-ane") { progress in
print(progress.fractionCompleted)
}
let asr = try Asr(plugin: .ane)
try await asr.load(from: modelDir)
```
## **Supported Models**
Explore our curated collections of compatible models:
Optimized models for Apple Neural Engine
Any GGUF format LLM and VLM models
## **Device Compatibility**
* Apple Neural Engine
* arm64
## **Next Steps**
Explore detailed documentation for all model types and learn their usage.