Implementation:Elevenlabs Elevenlabs python TurnConfigWorkflowOverride

Field	Value
source	Elevenlabs_Elevenlabs_python
domains	Conversational AI, Turn Management, Conversation Flow, Latency
last_updated	2026-02-15

Overview

Description

TurnConfigWorkflowOverride is a Pydantic model that defines turn-taking and timing configuration overrides for a conversational AI agent workflow in the ElevenLabs platform. It controls the temporal dynamics of conversations, including how long the agent waits for user responses, silence-based call termination, response eagerness, spelling patience, and speculative turn generation for reduced latency.

This model is auto-generated by Fern from the ElevenLabs API definition and inherits from UncheckedBaseModel. It provides fine-grained control over the conversational turn-taking behavior that directly impacts user experience and perceived responsiveness.

Usage

TurnConfigWorkflowOverride is used within agent workflow configuration to override default turn-taking behavior. It is essential for tuning the conversational experience, particularly for telephony agents where turn timing, silence handling, and response speed are critical to natural-sounding interactions.

Code Reference

Source Location

src/elevenlabs/types/turn_config_workflow_override.py

Class Signature

class TurnConfigWorkflowOverride(UncheckedBaseModel):
    ...

Import Statement

from elevenlabs.types import TurnConfigWorkflowOverride

I/O Contract

Field	Type	Required	Description
turn_timeout	Optional[float]	No	Maximum wait time for the user's reply before re-engaging the user.
initial_wait_time	Optional[float]	No	How long the agent will wait for the user to start the conversation if the first message is empty. If not set, uses the regular turn_timeout.
silence_end_call_timeout	Optional[float]	No	Maximum wait time since the user last spoke before terminating the call.
soft_timeout_config	Optional[SoftTimeoutConfigWorkflowOverride]	No	Configuration for soft timeout functionality. Provides immediate feedback during longer LLM responses.
turn_eagerness	Optional[TurnEagerness]	No	Controls how eager the agent is to respond. Low = less eager (waits longer), Standard = default eagerness, High = more eager (responds sooner).
spelling_patience	Optional[SpellingPatience]	No	Controls if the agent should be more patient when user is spelling numbers and named entities. Auto = model based, Off = never wait extra.
speculative_turn	Optional[bool]	No	When enabled, starts generating LLM responses during silence before full turn confidence is reached, reducing perceived latency. May increase LLM costs.

Usage Examples

Basic Turn Configuration

from elevenlabs.types import TurnConfigWorkflowOverride

turn_config = TurnConfigWorkflowOverride(
    turn_timeout=30.0,
    silence_end_call_timeout=120.0,
)

Low-Latency Eager Agent

from elevenlabs.types import TurnConfigWorkflowOverride

turn_config = TurnConfigWorkflowOverride(
    turn_timeout=15.0,
    turn_eagerness="high",
    speculative_turn=True,
    silence_end_call_timeout=60.0,
)

Patient Agent for Data Collection

from elevenlabs.types import TurnConfigWorkflowOverride

turn_config = TurnConfigWorkflowOverride(
    turn_timeout=45.0,
    initial_wait_time=10.0,
    turn_eagerness="low",
    spelling_patience="auto",
    silence_end_call_timeout=180.0,
)

Related Pages

• Elevenlabs_Elevenlabs_python_AgentConfig - Core agent configuration that includes first message settings
• Elevenlabs_Elevenlabs_python_TtsConversationalConfigInput - TTS configuration that interacts with turn timing
• Elevenlabs_Elevenlabs_python_AsrConversationalConfig - ASR configuration that feeds into turn detection
• Elevenlabs_Elevenlabs_python_BuiltInToolsInput - Built-in tools including skip_turn that relates to turn management
• Elevenlabs_Elevenlabs_python_GetAgentResponseModel - Full agent response model