Skip to main content
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 for installation and configuration. The ai-coustics LiveKit extras plugin provides 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 the official plugin 0.3.2 and the ai-coustics LiveKit extras plugin 0.25.0. 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 LiveKit extras plugin does not include Processor. Use the official plugin for speech enhancement.

​
Running both packages

In Python, the LiveKit extras plugin uses the ai_coustics.livekit import path. It can share an environment with the official plugin in Python and Node.js. Different import names do not make the objects interchangeable. Each VAD expects metadata from its own audio processing path. The ai-coustics quickstart uses only LiveKit extras plugin components in its RoomIO chain. To chain the official enhancement with the LiveKit extras plugin components, see the migration guide.

​
Authentication and provisioning

Keep all SDK and LiveKit keys on the server. Downloading a model is separate from authorizing a processing session. See authentication.

​
If you use Processor today

Plugin 0.2.0 Processor is not in the LiveKit extras plugin. Use the migration guide to move speech enhancement to the official plugin. Keep your deployment and lockfile while you evaluate the change.
  1. Record your baseline. Save the package versions, model ID, enhancement parameters, audio format and authentication configuration.
  2. 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 explains the difference between legacy energy thresholds and probability thresholds.

​
Questions

For the ai-coustics LiveKit extras plugin, open an issue in ai-coustics/livekit-extras. Include package versions, runtime, operating system, model IDs, audio geometry and a redacted error. For the official integration, use LiveKit’s documentation and community.