Skip to main content
STT Performance Layer is in PRIVATE BETA. The behavior described here is being rolled out gradually. Contact us 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.

Speech-to-Text Overview

The models available today and how to pick one.

How It Works

Where STT routing sits in the pipeline.