logo
ConsoleSign Up
AI Agent
Server
Introduction
Overview
Download SDK and Demo
Release Notes
Quick Start
Quick Start Voice Call
Quick Start Digital Human Video Call
Basic
Configuring LLM
Configuring ASR
Configuring TTS
AI Proactive Speech: Proactively Invoke LLM or TTS
Display Subtitles
Display User And Agent Status
Get AI Agent Status
Interrupt Agent
Advanced
Speech Segmentation Control
AI Short-Term Memory Management
Best Practices
Role-Playing System Prompt
Clone Voice
Interact with AI in IM and make voice calls
Use AI Agent with RAG
API Reference
Overview
Accessing Server APIs
Call API Online
Return Codes
Agent Configuration Management
POST
Register Agent
POST
Unregister Agent
POST
Update Agent
POST
List Agents
POST
Query Agents Details
Agent Instance Management
POST
Create Agent Instance
POST
Create Digital Human Agent Instance
POST
Update Agent Instance
POST
Delete Agent Instance
Agent Instance Control
POST
Trigger LLM
POST
Trigger TTS
POST
Query The Status of An AI Agent Instance
POST
Interrupt Agent Instance
POST
Get Agent Instance Context
POST
Reset Agent Instance Context
Callback
Receiving Callback
Exception Event Codes
FAQ
On this page

Speech Segmentation Control

Since LLM (Large Language Model) does not support streaming input, it is necessary to determine whether the user has finished speaking based on real-time ASR (Automatic Speech Recognition) results, and then request LLM to start a new round of Q&A.

To determine whether the user has finished speaking, check these parameters:

  • VADSilenceSegmentation
  • PauseInterval

Parameter Description

The two parameters that affect the determination of user's speech completion are in the ASR parameters of registering/updating agents and creating/updating agent instances. Please refer to Register Agent > Body > ASR Parameters for details.

Parameter NameTypeRequiredDescription
VADSilenceSegmentationNumberNoSets the duration (in milliseconds) of silence after which two utterances are no longer considered as one. Range: [200, 2000], Default: 500.
PauseIntervalNumberNoSets the duration (in milliseconds) within which two utterances are considered as one, enabling ASR multi-sentence concatenation. Range: [200, 2000]. ASR multi-sentence concatenation is only enabled when this value is greater than VADSilenceSegmentation.

Scenario Examples

ConfigurationQ&A Results
VADSilenceSegmentation = 500ms,
PauseInterval not set		User is determined to have spoken twice, resulting in 2 turns of Q&A
round 1:
- user: The weather is nice today. I want to go out
- assistant: Response 1 (interrupted by round 2)
Context: Empty
round 2:
- user: What about you?
- assistant: Response 2
Context: First Q&A round
VADSilenceSegmentation = 500ms,
PauseInterval = 1000ms		User is determined to have spoken once, resulting in 1 round of Q&A
- user: The weather is nice today. I want to go out. What about you?
- assistant: Response 1
Context: Empty

Best Practice Configurations

Note
If you're unsure which configuration works better, we recommend using Scenario 2 configuration.
ScenarioVADSilenceSegmentationPauseInterval
Scenario 1: Users speak in short, frequent bursts. E.g., companionship scenarios500msNot set
Scenario 2: Users have mixed-length content and are sensitive to latency. E.g., customer service scenarios500ms1000~1500ms
Scenario 3: Users typically speak for longer durations and are less sensitive to latency1000msNot set

Previous

Interrupt Agent

Next

AI Short-Term Memory Management

On this page

Back to top