If no setting is specifically added to PluginSettings, **phone\_call** is the default model used, if the detected language supports it. For other languages for which the model "phone\_call" does not exist, the model always falls back to the Google transcription model "**default**".
| Setting | Value | Scope |
| ---------------------- | --------------------------------------------------------------------------- | ------------- |
| GoogleRecognitionModel | The plain text name of the model.
Example: latest\_short
| Transcription |
#### Google Phrase List - Model Adaptation
{% hint style="info" %}
Introduced in DC2023.02d
{% endhint %}
The recognition of single words or phrases can be improved using model adaptation (Opens in new window or tab). This is useful for cases where certain phrases or words are said and can generate ambiguity with others. For example, if there is an ambiguity between "Claim" and "Plane", by using this feature it can give a boost to "Claim" and can be guessed more frequently.
The phrase set can be created using Google Cloud Console, where a name is given with the format projects/{project\_id}/locations/{location}/phraseSets/{phrase\_set\_id} for its reference.
If a reference is set in this setting, the adaptation model on that specific phrase set is going to be used in the transcriptions of the node.
{% hint style="info" %}
Note
That the name has to be exactly as it is stated in Google Cloud Console. The UCC logs indicate if the phrase set has been picked up successfully. If something went wrong, the error will be logged and it will fallback to no phrase list being picked up for the transcription.
{% endhint %}
| Setting | Value | Scope |
| ------------------------ | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------- |
| AdaptationModelPhraseSet | Optional phrase list set to provide commonly used phrases or single-words to give priority during transcription.
Example: project/955017966185/locations/global/phraseSets/Test
| Transcription |
## Microsoft Transcription
**Read more - Microsoft Speech-To-Text (STT)**
To setup Microsoft Speech transcription follow this guide: [Speech to text quickstart - Azure AI services | Microsoft Learn](https://learn.microsoft.com/en-us/azure/ai-services/speech-service/get-started-speech-to-text?tabs=windows%2Cterminal\&pivots=programming-language-csharp#prerequisites).
#### Prerequisites
* An Azure subscription
* A Speech Resource
* The Speech resource **Key** and **Region**
* DC2024.01
* DC2024.02 or higher
**DC2024.01**
The following settings need to be added in the "**PluginSettings**" list.
| Setting | Value | Scope |
| --------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | ------------ |
| CredentialsJson | json syntax
Configure UCC Speech-to-Text Transcription Code 1
| Transcriptor |
| PluginPath | Z:\UccService\Plugins\Wsp.Anywhere365.SpeechToTextEngine.Impl.MsCognitiveServices\1.0.x.x\Wsp.Anywhere365.SpeechToTextEngine.Impl.MsCognitiveServices.dll
| Transcriptor |
#### Configure UCC Speech-to-Text Transcription Code 1
Source row: **CredentialsJson**.
```
{ "SubscriptionKey": "", "Region": "" }
```
{% hint style="info" %}
Note
The correct version number (1.0.x.x) of the PluginPath will be automatically populated/updated when transcription is requested in the Dialogue Cloud OnePortal. The version number will vary and is dependent on bundle used.
{% endhint %}
Easy copy Microsoft Plugin
```
Z:\UccService\Plugins\Wsp.Anywhere365.SpeechToTextEngine.Impl.MsCognitiveServices\1.0.x.x\Wsp.Anywhere365.SpeechToTextEngine.Impl.MsCognitiveServices.dll
```
**DC2024.02 or higher**
The following settings need to be added in the "**PluginSettings**" list.
| Setting | Value | Scope |
| --------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | ------------ |
| CredentialsJson | json syntax
Configure UCC Speech-to-Text Transcription Code 2
| Transcriptor |
#### Configure UCC Speech-to-Text Transcription Code 2
Source row: **CredentialsJson**.
```
{ "SubscriptionKey": "", "Region": "" }
```
The following settings need to be added in the "**Settings**" list.
| Setting | Value | Scope |
| ---------------------------- | --------- | ------------- |
| TranscriptionServiceProvider | Microsoft | Transcription |
## (Optional) Voice transcription file (from STT)
### Introduction
The transcriptions can also be recorded(written) to a text file and saved .
### Prerequisite
The Transcription node must be utilized in Dialogue Studio during either the Incoming Call or InDialogue phase. If the Transcription node is not activated in these phases, the transcription process will not initiate, and no recordings will be made.
### Settings
| Setting | Value | Description |
| ---------------------- | ----- | ------------------------------------ |
| UseTranscriptRecording | true | If true, transcript will be recorded |
### Location
The Recording will be stored at the same location as the audio recordings, [Learn More](https://atlas.anywhere.now/operate/recording-and-interaction-data/manage-call-recordings)
### Data Format
In the example transcription below, you see that transcriptions have an "IsFinal" flag (see line nr. 33 below) that indicates if the transcription has completed. Intermediate results are also logged.
To determine the name or uri of the participant for which audio was transcribed, the TranscriptHistoryMessage.ParticipantId can be joined with the HistoryParticipant.Id (see line 6 and 12 below).
JSON
```
{
"Version":"1.0",
"DialogueId":"f748e530-6955-47a6-b7da-0de1fe0d8ea3",
"HistoryParticipants":[
{
"Id":0,
"ParticipantUri":"sip:+31612345678@drt002.abc.region.prd.dialogcloud.local;user=phone",
"ParticipantDisplayName":"tel:+31612345678",
"ParticipantType":"Customer"
},
{
"Id":1,
"ParticipantUri":"sip:ucctestuser1406@anywhere.now",
"ParticipantDisplayName":"ucctestuser1406@anywhere.now",
"ParticipantType":"Agent"
}
],
"ChatHistoryMessages":[
],
"TranscriptHistoryMessages":[
{
"Language":"nl",
"Transcript":"Hello",
"IsFinal":false,
"ParticipantId":0,
"Timestamp":"2020-01-06T11:38:34.8081659+01:00",
"Index":0
},
{
"Language":"nl",
"Transcript":"Hello world",
"IsFinal":true,
"ParticipantId":0,
"Timestamp":"2020-01-06T11:38:34.8236803+01:00",
"Index":0
}
],
"TranslationHistoryMessages":[
]
}
```
---
# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.
## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.
Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:
```
GET https://atlas.anywhere.now/operate/recording-and-interaction-data/configure-ucc-transcription.md?ask=&goal=
```
`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.
Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
