--- "@context": https://schema.org "@type": TechArticle "@id": https://www.twilio.com/docs/voice/conversationrelay/turn-detection#article headline: Turn detection for Conversation Relay description: Use Twilio Turn Detection with Conversation Relay to tell when a caller has finished speaking, so your AI voice agent doesn't interrupt callers who pause mid-sentence. url: https://www.twilio.com/docs/voice/conversationrelay/turn-detection inLanguage: en dateModified: 2026-11-13T16:20:39.000Z author: "@type": Organization name: Twilio Developer Education Team publisher: "@type": Organization name: Twilio --- # Turn detection for Conversation Relay > \[!NOTE] > > Turn Detection uses artificial intelligence or machine learning technologies. By enabling or using any features or functionalities within Programmable Voice that Twilio identifies as using artificial intelligence or machine learning technology, you acknowledge and agree to certain terms. Your use of these features or functionalities is subject to the terms of the [Predictive and Generative AI or ML Features Addendum](https://www.twilio.com/en-us/legal/ai-terms/predictive-generative-ai-features). > > Turn Detection isn't PCI compliant or a HIPAA Eligible Service. Don't use the [`turnDetection`](/docs/voice/twiml/connect/conversationrelay#conversationrelay-attributes) attribute in workflows that are subject to PCI or HIPAA regulations. Learn how to use Turn Detection with Conversation Relay to find out when a caller has finished speaking. Turn Detection helps your AI voice agent wait while a caller pauses to think, and respond promptly once the caller is done. See [Related reference documentation](#related-reference-documentation) to learn more about the `` attributes and WebSocket messages used in this guide. [All Conversation Relay guides](/docs/voice/guides/by-feature-product#conversation-relay) ## How Turn Detection works A voice AI agent needs to know when the caller has finished speaking. If the agent responds too early, it interrupts the caller. If it waits too long, the conversation feels slow. By default, Conversation Relay relies on the speech-to-text (STT) provider's silence handling to end the caller's turn. A silence threshold can't tell a caller who has finished from one who is pausing to think or using filler words, which leads to false interruptions. Turn Detection replaces that silence-based decision with a semantics-aware machine learning model built by Twilio. The model evaluates the caller's audio, not the transcript, in real time to tell whether the caller has completed their turn or is pausing mid-sentence. It runs in Twilio's media stack alongside STT, so it works with all supported STT providers and speech models except Deepgram Flux. For more on Flux, see [Limitations](#limitations). When the model decides the turn is complete, Conversation Relay sends the `prompt` message with `last` set to `true`, instead of waiting for an STT silence timer to expire. Turn Detection only affects when the turn ends. It doesn't change how Conversation Relay detects interruptions of the agent's speech. ## When to use Turn Detection Turn Detection is most useful when callers often pause in the middle of a thought. For example: * **Reading out long values.** Callers who recite confirmation codes, tracking numbers, or phone numbers tend to pause between groups of digits. * **Hesitant or thoughtful conversations.** In technical support or claims calls, callers often stop to collect their thoughts or use filler words such as "um" and "ah". * **Booking and reservations.** A caller might say "I'd like a table for... four people on Friday night." An agent that replies after the first pause breaks the flow of the conversation. ## Enable Turn Detection Set the `turnDetection` attribute to `true` on the `` noun: ```xml ``` No changes to your WebSocket server are required. Your application continues to receive [`prompt` messages](/docs/voice/conversationrelay/websocket-messages#prompt-message) and treats `last: true` as the end of the caller's turn. ```json { "type": "prompt", "voicePrompt": "I would like to book a table for Friday night.", "lang": "en-US", "last": true } ``` ## Receive turn state If your application needs more detail about the caller's turn, set the `includeInPrompt` attribute to `turn-state`. Conversation Relay then adds a `turnState` field to the `prompt` messages it sends. To receive the `start` and `interim` states, also set `partialPrompts` to `true`. ```xml ``` With this configuration, the prompt message that ends the caller's turn looks like this: ```json { "type": "prompt", "voicePrompt": "I would like to book a table for Friday night.", "lang": "en-US", "last": true, "turnState": "end" } ``` The `turnState` field can be `start`, `interim`, or `end`. For what each value means and when Conversation Relay sends it, see the [`prompt` message with turn state](/docs/voice/conversationrelay/websocket-messages#prompt-message-with-turn-state) reference. ## Tune when a turn ends * **`speechTimeout`:** Sets the longest silence that Conversation Relay allows before it ends the caller's turn, even if the model hasn't signaled that the turn is complete. If you don't set `speechTimeout`, Conversation Relay uses `1500` milliseconds. Valid values are integers from `600` to `5000`. * **`eotThreshold`:** Sets the confidence required to end a turn. Allowed values are `0.5` to `0.9`. The default is `0.8`. ## Limitations * **Deepgram Flux:** Turn Detection works with all supported STT providers and speech models except Deepgram Flux, which has its own turn detection model built in. If you enable `turnDetection` and also set `transcriptionProvider` to `Deepgram` and `speechModel` to `flux`, Conversation Relay bypasses Twilio Turn Detection and uses the Flux turn detection model. You can still use `includeInPrompt="turn-state"` with Flux. To tune Flux turn detection, see the `eotThreshold` and `speechTimeout` attributes in the [`` reference](/docs/voice/twiml/connect/conversationrelay#conversationrelay-attributes). ## Next steps Explore the following guides to build on what you've learned in this guide: * [Best practices for optimizing your Conversation Relay app](/docs/voice/conversationrelay/best-practices): Learn how to handle caller silence, prevent false interruptions, and stream text tokens. * [Update configuration during a call](/docs/voice/conversationrelay/dynamic-configuration): Change language, voice, and session settings over your WebSocket connection without ending the call. ## Related reference documentation Find reference documentation for the topics on this page. * [TwiML™ Voice: ``](/docs/voice/twiml/connect/conversationrelay): Reference documentation for the `turnDetection` and `includeInPrompt` attributes. * [Conversation Relay WebSocket Messages](/docs/voice/conversationrelay/websocket-messages): Reference documentation for the `prompt` message and its `turnState` field.