Skip to main content
The speech_model connection parameter lets you specify which model to use for streaming transcription.

Available models

For detailed setup and configuration of AssemblyAI-STT-3.7-Realtime-Agent, see the AssemblyAI-STT-3.7-Realtime-Agent quickstart. For prompting guidance, see the Prompting guide.

Set the model

Set the speech_model connection parameter when you open the WebSocket.