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

# STT Routing

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

<Note>
  STT Routing is in `PRIVATE BETA`. The behavior described here is being rolled
  out gradually. [Contact us](mailto:support@slng.ai) for access.
</Note>

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, and cost per turn.

## How it routes

Routing weighs several inputs together, not in isolation:

* **Language and accent** of the audio
* **Noise profile** of the environment
* **Regional availability** of models
* **Cost and latency** constraints

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

## Today

Until STT Routing is generally available, you select the STT model explicitly on each request. See the [Speech-to-Text Overview](/stt/overview) for the current model list and how to choose.

## Related

<CardGroup cols={2}>
  <Card title="Speech-to-Text Overview" icon="ear" href="/stt/overview">
    The models available today and how to pick one.
  </Card>

  <Card title="How It Works" icon="route" href="/execution-layer/how-it-works">
    Where STT routing sits in the pipeline.
  </Card>
</CardGroup>