> ## Documentation Index
> Fetch the complete documentation index at: https://mintlify.com/XDcobra/react-native-sherpa-onnx/llms.txt
> Use this file to discover all available pages before exploring further.

# Core Functions

> Core initialization and hardware acceleration detection functions

This module provides core functionality for testing library initialization and detecting hardware acceleration support on different platforms.

## testSherpaInit()

Test method to verify that the sherpa-onnx native library is loaded correctly.

```typescript theme={null}
function testSherpaInit(): Promise<string>
```

### Returns

<ResponseField name="Promise<string>" type="string">
  Resolves with a test message confirming the library is loaded.
</ResponseField>

### Example

```typescript theme={null}
import { testSherpaInit } from 'react-native-sherpa-onnx';

const result = await testSherpaInit();
console.log(result); // "Sherpa ONNX initialized successfully"
```

***

## getQnnSupport()

Check Qualcomm QNN (Qualcomm Neural Network) acceleration support on Android devices.

```typescript theme={null}
function getQnnSupport(modelBase64?: string): Promise<AccelerationSupport>
```

### Parameters

<ParamField path="modelBase64" type="string" optional>
  Optional base64-encoded model for session initialization test. If omitted, uses an embedded test model.
</ParamField>

### Returns

<ResponseField name="AccelerationSupport" type="object">
  <Expandable title="properties">
    <ResponseField name="providerCompiled" type="boolean">
      Whether QNN provider is compiled into the library
    </ResponseField>

    <ResponseField name="hasAccelerator" type="boolean">
      Whether a QNN-compatible hardware accelerator is available
    </ResponseField>

    <ResponseField name="canInit" type="boolean">
      Whether a model can be initialized using QNN
    </ResponseField>
  </Expandable>
</ResponseField>

### Platform Support

* **Android**: Full support on Qualcomm devices
* **iOS**: Returns all false

### Example

```typescript theme={null}
import { getQnnSupport } from 'react-native-sherpa-onnx';

const qnnSupport = await getQnnSupport();
if (qnnSupport.canInit) {
  console.log('QNN acceleration available');
  // Use provider: 'qnn' in model options
}
```

***

## getNnapiSupport()

Check NNAPI (Android Neural Networks API) acceleration support on Android devices.

```typescript theme={null}
function getNnapiSupport(modelBase64?: string): Promise<AccelerationSupport>
```

### Parameters

<ParamField path="modelBase64" type="string" optional>
  Optional base64-encoded model for session initialization test.
</ParamField>

### Returns

<ResponseField name="AccelerationSupport" type="object">
  See [getQnnSupport()](#getqnnsupport) for structure.
</ResponseField>

### Platform Support

* **Android**: Support varies by device and Android version
* **iOS**: Returns all false

### Example

```typescript theme={null}
import { getNnapiSupport } from 'react-native-sherpa-onnx';

const nnapiSupport = await getNnapiSupport();
if (nnapiSupport.canInit) {
  // Use provider: 'nnapi' in model options
}
```

***

## getXnnpackSupport()

Check XNNPACK (CPU-optimized) acceleration support.

```typescript theme={null}
function getXnnpackSupport(modelBase64?: string): Promise<AccelerationSupport>
```

### Parameters

<ParamField path="modelBase64" type="string" optional>
  Optional base64-encoded model for session initialization test.
</ParamField>

### Returns

<ResponseField name="AccelerationSupport" type="object">
  <Expandable title="properties">
    <ResponseField name="providerCompiled" type="boolean">
      Whether XNNPACK provider is compiled into the library
    </ResponseField>

    <ResponseField name="hasAccelerator" type="boolean">
      Returns true when providerCompiled is true (CPU-optimized execution)
    </ResponseField>

    <ResponseField name="canInit" type="boolean">
      Whether a model can be initialized using XNNPACK
    </ResponseField>
  </Expandable>
</ResponseField>

### Platform Support

* **Android**: Full support (CPU-optimized inference)
* **iOS**: Returns all false

### Example

```typescript theme={null}
import { getXnnpackSupport } from 'react-native-sherpa-onnx';

const xnnpackSupport = await getXnnpackSupport();
if (xnnpackSupport.canInit) {
  // Use provider: 'xnnpack' in model options
}
```

***

## getCoreMlSupport()

Check Core ML acceleration support on iOS devices with Apple Neural Engine.

```typescript theme={null}
function getCoreMlSupport(modelBase64?: string): Promise<AccelerationSupport>
```

### Parameters

<ParamField path="modelBase64" type="string" optional>
  Optional base64-encoded model for session initialization test.
</ParamField>

### Returns

<ResponseField name="AccelerationSupport" type="object">
  <Expandable title="properties">
    <ResponseField name="providerCompiled" type="boolean">
      True on iOS 11+ (Core ML framework available)
    </ResponseField>

    <ResponseField name="hasAccelerator" type="boolean">
      True when Apple Neural Engine is available (A11+ chips)
    </ResponseField>

    <ResponseField name="canInit" type="boolean">
      Whether a model can be initialized using Core ML
    </ResponseField>
  </Expandable>
</ResponseField>

### Platform Support

* **iOS**: Full support on iOS 11+ with Apple Neural Engine
* **Android**: Returns all false

### Example

```typescript theme={null}
import { getCoreMlSupport } from 'react-native-sherpa-onnx';

const coreMLSupport = await getCoreMlSupport();
if (coreMLSupport.hasAccelerator) {
  console.log('Apple Neural Engine available');
  // Use provider: 'coreml' in model options
}
```

***

## getAvailableProviders()

Get the list of available ONNX Runtime execution providers on the current device.

```typescript theme={null}
function getAvailableProviders(): Promise<string[]>
```

### Returns

<ResponseField name="Promise<string[]>" type="string[]">
  Array of provider names (e.g., `["CPU", "NNAPI", "QNN", "XNNPACK"]`).
</ResponseField>

### Platform Support

Requires the ONNX Runtime Java bridge from the onnxruntime AAR.

### Example

```typescript theme={null}
import { getAvailableProviders } from 'react-native-sherpa-onnx';

const providers = await getAvailableProviders();
console.log('Available providers:', providers);
// ["CPU", "XNNPACK", "QNN"] on Qualcomm Android
// ["CPU", "CoreML"] on iOS with Neural Engine
```

***

## Types

### AccelerationSupport

Result type for hardware acceleration queries.

```typescript theme={null}
interface AccelerationSupport {
  /** Whether the provider is compiled into the library */
  providerCompiled: boolean;
  
  /** Whether compatible hardware accelerator is available */
  hasAccelerator: boolean;
  
  /** Whether a model session can be initialized with this provider */
  canInit: boolean;
}
```

***

## See Also

* [Model Path Utilities](/api/model-path) - Utilities for resolving model paths
* [STT API](/api/stt/create-stt) - Speech-to-text API
* [TTS API](/api/tts/create-tts) - Text-to-speech API