> ## Documentation Index
> Fetch the complete documentation index at: https://slng.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# STT Performance Layer

> The first stage of the execution layer routes each turn's audio to the transcription model best suited to it, balancing accuracy, latency, activity detection and diarization.

> [!NOTE]
>
> STT Performance Layer is in `PRIVATE BETA`. The behavior described here is being rolled out gradually. [Contact us](mailto:support@slng.ai) for access.

The first stage of the execution layer. When audio arrives, it is routed to the right STT model for that specific interaction.

A Hindi caller in Mumbai gets a different model than an English caller in New York. A noisy environment may route to a model with better noise handling. The layer balances accuracy, latency, activity detection and diarization.

## What is it?

The STT performance layer gives you access to several tools across STT models like:

* **Noise cancellation** for different types of audio
* **VAD** for all different speakers in your input audio
* **Language routing** across different models
* **Diarization** for accurate transcription metadata

For voice agent calls, routing happens per turn. Each turn can route to the model best suited to that specific audio segment.

## Related

> **[Speech-to-Text Overview](https://slng.mintlify.site/stt/overview.md)**
>
> The models available today and how to pick one.

> **[How It Works](https://slng.mintlify.site/execution-layer/how-it-works.md)**
>
> Where STT routing sits in the pipeline.


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