> ## 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

> The CPU inference runtime used by the ai-coustics SDK.

## Overview

AirTen executes ai-coustics models locally on the CPU. Applications use it through the SDK; they do not need to integrate a separate inference framework such as ONNX Runtime, PyTorch or TensorFlow.

## Characteristics

* **CPU inference:** A GPU is not required for SDK audio processing.
* **SDK-managed runtime:** Install the binding and its supported native library for your platform. See the [language bindings](/reference/sdk/language-bindings).
* **Stateful processing:** Each independent audio stream needs its own processing state. See [streams and state](/reference/concepts/streams-and-state).

Local inference describes where audio processing happens. Model downloads, authorization and telemetry have separate network requirements, described in [SDK telemetry](/reference/concepts/sdk-telemetry).

## Model support

AirTen executes `.aicmodel` files. Match the model to the core SDK version using the [model catalog](/reference/sdk/models) and [compatibility matrix](/reference/sdk/compatibility-matrix). A language binding version and a core SDK version are different identifiers.

## Performance

Processing time depends on the model, CPU, audio configuration and competing workload. A fixed algorithmic delay does not guarantee a fixed execution time or that every call finishes within its audio frame budget.

Measure processing duration, memory use and concurrent-stream capacity on the hardware and resource limits you intend to deploy. Include resampling, application buffering and other pipeline stages in end-to-end measurements.

Use the [latency guide](/reference/concepts/latency) to interpret SDK delay and the [performance guide](/reference/concepts/performance) to evaluate runtime cost. The [deployment guide](/production/deployment) connects these measurements to readiness and overload handling.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.