Turn Detection

Turn Detection identifies when a speaker has finished their conversational turn and it’s appropriate for an AI to respond. It solves a critical problem in voice AI: respond too early and you interrupt the speaker; wait too long and the conversation feels awkward.

How It Works

Turn detection analyzes audio through a multi-stage pipeline:

1. Voice Activity Detection (VAD): Detects when someone is speaking
2. Audio Buffering: Collects speech segments for analysis
3. AI Analysis: Examines speech patterns, content, and context to predict turn completion
4. Turn Signals: Sends TurnStarted and TurnEnded signals into the pipeline so the agent knows when to interrupt and when to respond

The key insight is distinguishing between “I’m pausing to think” and “I’m done talking”—something simple silence detection can’t do.

Turn Detection vs VAD

	VAD	Turn Detection
Question	”Is someone speaking?"	"Has the speaker finished?”
Output	Speech start/end timestamps	TurnStarted / TurnEnded turn signals
Intelligence	Simple audio analysis	Conversational context
Best for	Detecting presence	Knowing when to respond

Vision Agents’ turn detection uses VAD under the hood, then applies neural models to determine turn completion.

Available Plugins

Plugin	Description
Smart Turn	Combines Silero VAD, Whisper features, and neural turn completion models
Vogent	Neural turn detection with high accuracy prediction

Some STT plugins also include built-in turn detection via VAD, which means no separate plugin is needed:

STT Plugin	Turn Detection
Deepgram	Built-in with eager_turn_detection option
ElevenLabs	Built-in via VAD commit strategy

For Realtime APIs (OpenAI, Gemini, AWS Bedrock, Qwen), turn detection is built-in at the model level—no separate plugin needed.

When an STT plugin provides built-in turn detection, the Agent automatically ignores any external TurnDetector plugin to prevent conflicts.

Use Cases

• Voice Assistants: Respond at the right moment without interrupting
• Customer Service Bots: Natural conversation flow with customers
• Real-time Translation: Capture complete thoughts before translating
• Meeting Intelligence: Identify natural break points for summarization
• Interview Tools: AI interviewers that don’t interrupt

Next Steps

• Interruption Handling — How to use turn detection in your agent (setup, tuning, troubleshooting)
• Smart Turn — Configure the Smart Turn plugin
• Vogent — Alternative turn detection option