> ## 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.

# Which LiveKit plugin to use

> Choose the official plugin for speech enhancement or the ai-coustics-maintained plugin for dedicated VAD and Tyto.

**ai-coustics** models are available through two LiveKit integrations with different APIs and authentication paths.

The official LiveKit plugin is the primary path for speech enhancement. Follow LiveKit's [noise cancellation documentation](https://docs.livekit.io/transport/media/noise-cancellation/) for installation and configuration.

The ai-coustics-maintained plugins provide standalone voice activity detection (VAD) and Tyto audio-quality analysis, billed through ai-coustics. These capabilities are unavailable in the compared official-plugin release.

## Which plugin for what

This comparison covers official plugin 0.3.2 and ai-coustics-maintained plugin 0.2.0 as of September 18, 2026.

| Need                                                              | Integration                                                                | Next step                                                                                 |
| ----------------------------------------------------------------- | -------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------- |
| Speech enhancement with Quail Multi Speaker or Quail Voice Focus  | Official `livekit-plugins-ai-coustics` / `@livekit/plugins-ai-coustics`    | [LiveKit noise cancellation](https://docs.livekit.io/transport/media/noise-cancellation/) |
| Voice activity detection coupled to the official enhancement path | Official plugin's VAD adapter, with its accompanying enhancement component | Keep the official components together.                                                    |
| Standalone voice activity detection with a dedicated model        | `ai-coustics-livekit-plugin` / `@ai-coustics/livekit-plugin`               | [Complete VAD quickstart](/models/get-started/livekit-quickstart)                         |
| Tyto audio-quality analysis                                       | ai-coustics-maintained plugin's `Analyzer` and `collector`                 | [Add Tyto](/models/get-started/livekit-quickstart#audio-quality-analysis)                 |

The official plugin's VAD adapter in this release consumes metadata from its accompanying enhancement component. It is not interchangeable with the dedicated `VAD(model=...)` / `new VAD({ model })` API. The ai-coustics-maintained release also includes `Processor` for existing enhancement integrations; new enhancement projects should use the official plugin.

## Running both plugins today

<Warning>
  The two Python distributions install into the same `livekit/plugins/ai_coustics/` directory. They cannot safely coexist in one Python environment. Use separate environments until you have verified that a released package resolves the conflict.
</Warning>

A mixed Python installation can produce an `ImportError` for `Model` or `Analyzer`, or a `TypeError` for `VAD(model=...)`. Recreate an isolated environment with the single distribution your application needs. Do not use installation order to select an implementation.

Node packages use different import names. That distinction does not make their objects interchangeable: each VAD expects metadata from its own audio processing path. The [ai-coustics quickstart](/models/get-started/livekit-quickstart) uses only the ai-coustics-maintained components in its RoomIO chain.

Evaluate standalone VAD or Tyto in a separate project while retaining your official enhancement deployment.

## Authentication and provisioning

| Concern                      | Official plugin                                         | ai-coustics-maintained plugin                                 |
| ---------------------------- | ------------------------------------------------------- | ------------------------------------------------------------- |
| LiveKit Cloud authentication | Default Cloud authentication and metering               | Uses a separate ai-coustics SDK key for SDK usage             |
| Explicit ai-coustics key     | `Auth.ai_coustics_api(...)` / `Auth.aiCousticsApi(...)` | `AIC_SDK_LICENSE`, `license_key` / `licenseKey`               |
| Models                       | Select from the official plugin's exposed model choices | Provision `.aicmodel` files and load matching `Model` objects |
| VAD activation               | Use the adapter with its accompanying enhancement path  | Pass `vad` to the session and `vad.processor` to RoomIO       |
| Tyto activation              | No `Analyzer` API in the compared release               | Add `analyzer.collector` to RoomIO and handle result events   |

Keep all SDK and LiveKit keys on the server. Downloading a model is separate from authorizing a processing session. See [authentication](/models/get-started/authenticate-apps).

## If you use Processor today

Plugin 0.2.0 still exposes `Processor`. Keep your deployment and lockfile while evaluating official enhancement separately.

1. **Record your baseline.** Save the package versions, model ID, enhancement parameters, audio format and authentication configuration.
2. **Configure official enhancement.** Follow the [official installation and model selection instructions](https://docs.livekit.io/transport/media/noise-cancellation/). Its `audio_enhancement()` / `audioEnhancement()` factory replaces a manually provisioned enhancement `Processor` in that environment. Model names do not guarantee identical weights across versions.
3. **Review VAD separately.** The dedicated VAD and official adapter have different model and metadata paths. Do not carry the dedicated `vad.processor` into an official-plugin chain or copy legacy sensitivity values without reviewing their ranges.
4. **Compare and recover.** Use the same recordings and downstream providers to compare enhancement, speech boundaries and response latency. Test room disconnect and reconnect. Restore the previous deployment and its lockfile if the new combination fails acceptance.

Do not combine a package change, model change and VAD tuning into one unmeasured rollout. The [dedicated VAD migration reference](/reference/deprecated/energy-vad-to-dedicated-vad) explains the difference between legacy energy thresholds and probability thresholds.

## Questions

For the ai-coustics-maintained plugin, open an issue in [ai-coustics/livekit-plugins](https://github.com/ai-coustics/livekit-plugins/issues). Include package versions, runtime, operating system, model IDs, audio geometry and a redacted error. For the official integration, use [LiveKit's documentation and community](https://docs.livekit.io/home/get-started/intro-to-livekit/).