Configuring Models

Multiple models can be stacked together as a list in a single request. Each model has a modelType and a modelConfig key. 
Key
Description
modelType
Used to identify the type/name of model being enabled
modelConfig
Used to send additional configuration specific to the model
Some of the models are dependant on the outputs of other models. This dependency can be understood under the  Flow of Data and Stacking Models Section.
Quick Links to Configure Models
Enable & Configure Models
​Speech-to-text​
Emotion & Tone Detection
​Sentiment Detection​
​Conversation Type Detection​
​Questions & Responses​
​Action Items & Follow-ups​
​Topic Detection​
​Conversation Summary​
​Screen Activity ​
​Screengrabs (Chapter API)​
​Enable Speech Insights (BETA)​
​Enable Search (BETA)​
​
Example: How to Request for Question & Responses model on a Transaction ID.
Step 1: Finding out the Dependencies.
Model Dependency and flow of data
As shown in the above Flow Diagram question_response model is dependant on the outputs of emotion_analysis , sentiment_analysis, speech_type_analysis  models and these models are dependants on the outputs of speech_to_text with speaker_seperation enabled.
Therefore a sample request for question_response modelwould look like this. (refer to the Example given below)
Sample Model Configuration 
1
{
2
	"txnId": "txn-dummy-1623245791219",
3
    "enableModels":[
4
        {
5
        "modelType":"speech_to_text",
6
        "modelConfig":{
7
            "automatic_punctuation" : true,
8
            "custom_vocabulary":[],
9
            "speaker_seperation":{
10
                "num_speakers":2
11
            },
12
            "enableKeywords":true,
13
            "aggressiveness": 3,
14
            "enableSuggestedIntents":false,
15
            "topics": {
16
                "threshold": 0.5
17
            }
18
            }
19
        },
20
        {
21
            "modelType":"emotion_analysis"
22
        },
23
        {
24
            "modelType":"sentiment_analysis"
25
        },
26
        {
27
            "modelType":"speech_type_analysis"
28
        },
29
        {
30
            "modelType":"action_items",
31
            "modelConfig":{
32
                    "priority": 3
33
            } 
34
        },
35
        {
36
            "modelType":"question_response",
37
            "modelConfig":{
38
                "quality" : 1
39
            }
40
        },
41
        {
42
            "modelType":"extractive_summary"
43
        },
44
        {
45
            "modelType":"meeting_topics"
46
        },
47
        {
48
            "modelType":"screengrabs",
49
            "modelConfig":{
50
                "ocr":{
51
                    "enable":true
52
                }
53
            }
54
        },
55
        {
56
            "modelType":"screen_activity"
57
        },
58
        {
59
            "modelType":"data_insights",
60
            "modelConfig": {
61
                "dead_air": {
62
                    "threshold": 3000
63
                }
64
            }
65
        }
66
​
67
    ]
68
}
Copied!
​
​
​

Async Speech Analytics API - Previous

POST Compute Request

Speech-to-text

Last modified 5mo ago

Copy link

Contents

Quick Links to Configure Models

Example: How to Request for Question & Responses model on a Transaction ID.

Sample Model Configuration