> ## 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.

# Examples

> Browse example code for the ai-coustics SDK across all supported languages.

Find examples of model loading, audio enhancement, VAD, analysis and benchmarking for your SDK binding.

<Note>
  Native SDK examples and the ai-coustics-maintained LiveKit plugins require an `AIC_SDK_LICENSE` environment variable. The [browser quickstart](/reference/sdk/language-bindings/wasm) keeps the SDK key on a backend and gives the browser a short-lived token. Get your license key from the [ai-coustics developer platform](https://developers.ai-coustics.com). LiveKit Cloud authentication applies only to the LiveKit-owned plugins.
</Note>

Start with the [SDK quickstart](/models/get-started/sdk-quickstart) for a small file-processing example. The links below use released versions; install the matching binding and the example's dependencies.

## LiveKit

<CardGroup cols={1}>
  <Card title="LiveKit quickstart" href="/models/get-started/livekit-quickstart">
    Add ai-coustics speech enhancement, VAD and audio-quality analysis to a LiveKit Python or Node.js voice agent.
  </Card>
</CardGroup>

## Python

<CardGroup cols={2}>
  <Card title="Basic usage" href="https://github.com/ai-coustics/aic-sdk-py/blob/3.3.0/examples/enhancement.py">
    Download a model from the CDN, load it, configure a processor and enhance audio in a synchronous workflow.
  </Card>

  <Card title="Async usage" href="https://github.com/ai-coustics/aic-sdk-py/blob/3.3.0/examples/enhancement_async.py">
    Asynchronous version of the basic example using `async`/`await` for model downloading and audio processing.
  </Card>

  <Card title="File enhancement" href="https://github.com/ai-coustics/aic-sdk-py/blob/3.3.0/examples/enhance_files.py">
    Enhance WAV files from disk, downmixing multi-channel input to mono, with progress reporting.
  </Card>

  <Card title="Voice activity detection" href="https://github.com/ai-coustics/aic-sdk-py/blob/3.3.0/examples/vad.py">
    Run a dedicated VAD model, tune sensitivity and hold duration and read speech decisions from the VAD context.
  </Card>

  <Card title="Audio analysis" href="https://github.com/ai-coustics/aic-sdk-py/blob/3.3.0/examples/analyze_file.py">
    Score an audio file with the Tyto analysis model across five-second windows.
  </Card>

  <Card title="Benchmark" href="https://github.com/ai-coustics/aic-sdk-py/blob/3.3.0/examples/benchmark.py">
    Benchmark real-time processing throughput by spawning parallel processing sessions.
  </Card>
</CardGroup>

## Pipecat

The [Pipecat quickstart](/models/get-started/pipecat-quickstart#adapt-this-example) explains how to continue from loopback to the conversational example below, including provider credentials, VAD ownership and recording behavior. Use the matching Pipecat 1.11.0 dependencies.

<CardGroup cols={2}>
  <Card title="Speech enhancement (AICFilter)" href="https://github.com/pipecat-ai/pipecat/blob/v1.11.0/examples/voice/voice-aicoustics.py">
    Voice agent that enhances incoming audio with the AICFilter.
  </Card>

  <Card title="Voice activity detection" href="https://github.com/pipecat-ai/pipecat/blob/v1.11.0/examples/voice/voice-aicoustics-vad-only.py">
    VAD event check without STT, LLM or TTS services. This example also applies enhancement before VAD.
  </Card>
</CardGroup>

## Node.js

<CardGroup cols={2}>
  <Card title="Basic usage" href="https://github.com/ai-coustics/aic-sdk-node/blob/0.25.0/examples/enhancement.js">
    Download a model, create a processor and enhance audio samples with the Node.js SDK.
  </Card>

  <Card title="Async enhancement" href="https://github.com/ai-coustics/aic-sdk-node/blob/0.25.0/examples/enhancement-async.js">
    Enhance audio with `ProcessorAsync` and process concurrent streams without blocking the event loop.
  </Card>

  <Card title="File processing" href="https://github.com/ai-coustics/aic-sdk-node/blob/0.25.0/examples/file-processing.js">
    Read a WAV file, enhance it with configurable model and enhancement level and write the result to disk.
  </Card>

  <Card title="Voice activity detection" href="https://github.com/ai-coustics/aic-sdk-node/blob/0.25.0/examples/vad.js">
    Run a dedicated VAD model and read speech decisions from the VAD context.
  </Card>

  <Card title="Async voice activity detection" href="https://github.com/ai-coustics/aic-sdk-node/blob/0.25.0/examples/vad-async.js">
    Run `VadAsync` on a worker thread, including detection combined with enhancement.
  </Card>

  <Card title="Audio analysis" href="https://github.com/ai-coustics/aic-sdk-node/blob/0.25.0/examples/analysis.js">
    Buffer audio with `Analyzer` and score it with Tyto using blocking or async analysis.
  </Card>
</CardGroup>

## Rust

<CardGroup cols={2}>
  <Card title="Basic usage" href="https://docs.rs/aic-sdk/0.25.0/aic_sdk/docs/examples/enhancement/index.html">
    Download a model at runtime, configure a processor with enhancement parameters and process audio.
  </Card>

  <Card title="Voice activity detection" href="https://docs.rs/aic-sdk/0.25.0/aic_sdk/docs/examples/vad/index.html">
    Run a dedicated VAD model and read speech decisions from the VAD context.
  </Card>

  <Card title="Audio analysis" href="https://docs.rs/aic-sdk/0.25.0/aic_sdk/docs/examples/analyze_file/index.html">
    Score an audio file with the Tyto analysis model.
  </Card>

  <Card title="Parallel async" href="https://docs.rs/aic-sdk/0.25.0/aic_sdk/docs/examples/parallel_async/index.html">
    Process multiple streams concurrently with the async API.
  </Card>

  <Card title="Benchmark" href="https://docs.rs/aic-sdk/0.25.0/aic_sdk/docs/examples/benchmark/index.html">
    Multi-threaded benchmark that measures real-time processing throughput across parallel sessions.
  </Card>

  <Card title="Build-time model download" href="https://docs.rs/aic-sdk/0.25.0/aic_sdk/docs/examples/build_time_download/index.html">
    Download a model at build time and embed it directly into your binary using the `include_model!` macro.
  </Card>
</CardGroup>

## C

<CardGroup cols={2}>
  <Card title="Enhancement" href="https://github.com/ai-coustics/aic-sdk-c/blob/0.25.0/examples/enhancement.c">
    Load a model from file, create a processor and enhance mono audio using the C API.
  </Card>

  <Card title="Voice activity detection" href="https://github.com/ai-coustics/aic-sdk-c/blob/0.25.0/examples/vad.c">
    Create an `AicVad` from a dedicated VAD model and read speech decisions, with full error checking.
  </Card>

  <Card title="Audio analysis" href="https://github.com/ai-coustics/aic-sdk-c/blob/0.25.0/examples/analyzer.c">
    Buffer audio through a collector and score it with the Tyto analysis model.
  </Card>
</CardGroup>

## C++

<CardGroup cols={2}>
  <Card title="Basic usage" href="https://github.com/ai-coustics/aic-sdk-cpp/blob/0.25.0/example/enhancement.cpp">
    Load a model, configure a processor and enhance mono audio using the C++ API.
  </Card>

  <Card title="Voice activity detection" href="https://github.com/ai-coustics/aic-sdk-cpp/blob/0.25.0/example/vad.cpp">
    Run a dedicated VAD model and read speech decisions from the VAD context.
  </Card>

  <Card title="Audio analysis" href="https://github.com/ai-coustics/aic-sdk-cpp/blob/0.25.0/example/analyzer.cpp">
    Buffer audio through a collector and score it with the Tyto analysis model.
  </Card>
</CardGroup>

## WebAssembly

<CardGroup cols={1}>
  <Card title="Browser quickstart" href="/reference/sdk/language-bindings/wasm">
    Load a model and enhance audio in the browser with the WASM SDK.
  </Card>
</CardGroup>


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