Get Punctuated Transcripts
// Overview
Leveraging the unique interactionIdentifier provided upon successfully declaring an audio interactiondeclaring the audio interaction, the Punctuated Transcript endpoint lets you instantly retrieve a detailed sentence-by-sentence transcript with precise timings, confidence scoresconfidence scores, and speaker labels.
When this GET request successfully executes, an HTTP status will be returned to indicate the request was successful, along with a JSON response providing detailed transcription output.
{
"sentenceSegments": [
{
"participant": "participantOne",
"startTimeOffset": 1410,
"endTimeOffset": 3210,
"phrase": "Thank you for calling America phone service.",
"score": 0.99137425
},
{
"participant": "participantOne",
"startTimeOffset": 3210,
"endTimeOffset": 5570,
"phrase": "This is Adam speaking, how may I be of service.",
"score": 0.99325925
},
...
],
"redactionSegments": [
{
"startTimeOffset": 24650,
"endTimeOffset": 27530,
"result": "CVV",
"score": 0
},
...
]
}If an error occurs when requesting to declare the interaction, a standard HTTP status will be retuned to indicate the request was unsuccessful, along with a JSON response containing additional details to assist with troubleshooting.
// Request Parameters & Code Examples
var client = new RestClient("https://api.elevateai.com/v1/interactions/{interctionIdentifier}/transcripts/punctuated");
client.Timeout = -1;
var request = new RestRequest(Method.GET);
request.AddHeader("X-API-Token", "{Your API Token}");
request.AddHeader("Content-Type", "application/json");
request.AddHeader("Accept-Encoding", "gzip, deflate, br");
IRestResponse response = client.Execute(request);
Console.WriteLine(response.Content);// Response Schema
Schema
Element | Type | Description |
|---|---|---|
sentenceSegments | array of objects | Ordered list of each sentence spoken, excluding redacted phrases |
sentenceSegments/participant | string | Speaker associated with sentence, will be either participantOne or participantTwo |
sentenceSegments/startTimeOffset | number | Start time of sentence, in milliseconds |
sentenceSegments/endTimeOffset | number | End time of sentence, in milliseconds |
sentenceSegments/phrase | string | Punctuated sentence, with any redacted segments, represented by "# # # #" |
sentenceSegments/score | float | Confidence score |
redactionSegments | array of objects | List of details associated with each redacted segment |
redactionSegments/startTimeOffset | number | Start time of redacted phrase, in milliseconds |
redactionSegments/endTimeOffset | number | End time of redacted phrase, in milliseconds |
redactionSegments/result | string | Reason for redaction, will be CVV, Credit Card, or Social Security |
redactionSegments/score | float | Confidence score |
Need more help? Contact the ElevateAI Support team.