Overview
This API enables real-time interaction between client applications and the Agent Assist backend over a WebSocket connection. It provides information to support live agent interactions during a conversation, such as sound amplitude, dialog state, user sentiment, task suggestions, and more.
-
Protocol: WebSocket (
wss) -
Authentication: Token-based (via session token)
-
Content-Type:
application/json -
Schema Format: AsyncAPI 3.0
Access Requirements
-
WebSocket client must connect to a valid
wss://endpoint provided by the deployment. -
Connection must be authenticated using a valid token.
-
All messages are exchanged in JSON format.
Real-Time Server Messages
The following messages are sent from the server to the connected client:
Sound Info
|
Field |
Type |
Description |
|---|---|---|
|
|
Integer |
Current amplitude level of the speaker (0–2) |
AI Info
|
Field |
Type |
Description |
|
|
String |
POSITIVE, NEGATIVE, or NEUTRAL |
|
|
String |
Detected emotion label |
|
|
Boolean |
Boolean flag for anger detection |
|
|
String |
Current user intents |
|
|
String |
Agent emotional state |
|
|
Array |
List of key-value task objects |
|
|
Array |
Remaining tasks |
|
|
String |
Next task to perform |
|
|
String |
Suggested response prompt |
Dialog Info
|
Field |
Type |
Description |
|
|
Integer |
Latest dialog sequence ID |
|
|
Array |
List of utterance steps |
|
|
String |
Current agent utterance (if not final) |
|
|
String |
Current user utterance (if not final) |
Dialog Diff
|
Field |
Type |
Description |
|
|
Integer |
Dialog step ID |
|
|
Enum |
USER or AGENT |
|
|
String |
Text spoken |
|
|
Integer |
Epoch start of speech |
|
|
Integer |
Epoch end of speech |
|
|
Boolean |
Boolean flag for utterance finality |
Call Info
|
Field |
Type |
Description |
|
|
Enum |
Call state (ACTIVE, CLOSED, etc.) |
|
|
String |
Optional error details |
Verification Result
|
Field |
Type |
Description |
|
|
String |
Result label |
|
|
String |
Status value |
|
|
Enum |
LOW_RISK, MEDIUM_RISK, HIGH_RISK |
|
|
Number |
Overall score |
|
|
String |
ID of matched fraudster (if any) |
|
|
String |
Blocklist entry ID |
|
|
String |
Agent message |
|
|
String |
UI message |
|
|
Number |
Log-likelihood ratio score |
|
|
Number |
Normalized log-likelihood ratio score |
|
|
Integer |
Number of speech frames |
|
|
Integer |
Size of blocklist |
|
|
Integer |
Number of matches |
Voice Info
|
Field |
Type |
Description |
|
|
Enum |
GENUINE, SPOOFED, SYNTHETIC, etc. |
|
|
Number |
Posterior score |
|
|
Enum |
OK_DATA, LOW_DATA, etc. |
|
|
Boolean |
SAT validity |
|
|
String |
Predicted gender |
|
|
Integer |
Predicted age |
Error Info
|
Field |
Type |
Description |
|
|
String |
Error summary |
|
|
String |
Detailed error explanation |
Call Summary
|
Field |
Type |
Description |
|
|
String |
Call summary text |
TTS Detection
|
Field |
Type |
Description |
|
|
Enum |
GENUINE or SPOOFED |
|
|
Number |
Detection confidence score |
ANI Validation Results
|
Field |
Type |
Description |
|
|
String |
Phone number used in call |
|
|
Integer |
Trust score (0–100) |
Business Flow Info
|
Field |
Type |
Description |
|
|
String |
Unique instance ID |
|
|
Enum |
NOT_STARTED, RUNNING, COMPLETED, etc. |
|
|
String |
Detected intent triggering the flow |
|
|
Array |
List of entity values and matched prompts |
Business Flow Diff
|
Field |
Type |
Description |
|
|
String |
Flow ID |
|
|
Enum |
Updated flow status |
|
|
String |
Changed entity |
|
|
String |
New value |
Attached Data
|
Field |
Type |
Description |
|
|
Array |
Array of key-value maps of attached metadata |
Client-Initiated Commands
The client may send commands via the following channel:
|
Field |
Type |
Description |
|
|
Enum |
One of GET_DIALOG, GET_BUSINESSFLOW_INSTANCES, etc. |
|
|
Object |
Parameters such as |
Example Topics and Channels
|
Channel |
Direction |
Purpose |
|
|
receive |
Send client command |
|
|
send |
Sound level updates |
|
|
send |
AI analysis and task suggestions |
|
|
send |
Full dialog information |
|
|
send |
Dialog deltas |
|
|
send |
Call status |
|
|
send |
Voice verification result |
|
|
send |
Voice analysis (liveness, age, etc.) |
|
|
send |
Error messages |
|
|
send |
Post-call summary |
|
|
send |
TTS spoofing detection |
|
|
send |
Caller number validation |
|
|
send |
Business flow state snapshot |
|
|
send |
Business flow change notification |
|
|
send |
Custom metadata injection |