> ## Documentation Index
> Fetch the complete documentation index at: https://docs.ai-coustics.com/llms.txt
> Use this file to discover all available pages before exploring further.

# AirTen

> Proprietary real-time neural network inference engine powering all SDK implementations.

## Overview

AirTen is our CPU-based neural network inference engine. It runs without external dependencies like ONNX or ML frameworks, providing low-latency inference suitable for real-time audio processing.

## Characteristics

* **CPU-only**: No GPU or external inference runtimes
* **No framework dependencies**: Self-contained, no PyTorch or TensorFlow
* **Deterministic latency**: Suitable for real-time audio processing

## Model Support

AirTen executes our model binaries (.aicmodel files). Supported models and specifications are documented on our [Models Guide](/reference/sdk/models).

## Performance

* Sub-frame latency on modern CPUs
* Minimal memory footprint

<Warning>
  Performance varies with CPU architecture and model complexity.
</Warning>

For more information see our [Latency guide](/reference/concepts/latency) and [Performance guide](/reference/concepts/performance).