Skip to main content
Smart Turn uses neural models (Silero VAD + Whisper features) to detect when a speaker has completed their turn. Provides natural conversation flow without relying solely on silence detection.
Vision Agents uses Stream Video for real-time WebRTC transport by default. External WebRTC transports are supported as well. Most AI providers offer free tiers to get started.

Installation

Quick Start

Models download automatically on first use.

Parameters

Turn Signals

Next Steps

Build a Voice Agent

Get started with voice

Build a Video Agent

Add video processing