Latest revision as of 04:01, 29 May 2024

• 5.19 • 5.3 • 5.8

Speech To Text Integration (STT)

Integration Accounts > add account > Speech to Text

Speech To Text (STT) integration enables your contact center to use speech-to-text functionality to transcribe voice calls and save the transcriptions to interaction records. Full-text transcripts are searchable and include sentiment attributes (if Natural Language Understanding is enabled).

Bright Pattern integrates with STT providers such as IBM Watson and Google.

Select the type of STT integration.

Google Synchronous Properties

Google's Cloud Speech API converts audio to text. Synchronous STT is limited to 1 recordings, making is useful for Conversational IVR . To transcribe calls, see Streaming STT below. In the Properties dialog, enter the credentials for your Google synchronous STT instance as follows. This allows Bright Pattern to access your STT resource and use it in interactions.


	Google STT requires a payment method to be attached to the account; without this, the STT service would silently not work, and there would be an error in the Google API dashboard.

Google Synchronous STT integration account properties.

Name: The unique name for this integration account (any)

Type: By default, “Google synchronous STT” because you selected this type when adding the account.

Use enhanced mode: When enabled, Use enhanced mode allows you to use the Cloud Speech APIs enhanced model for phone calls. This setting allows for more accurate transcriptions of voice calls on conversational IVR scenarios. Enhanced mode is enabled when initializing Google Speech-to-Text.

URL: By default, https://speech.googleapis.com/v1/

API key

The service key ID that is used to authenticate Google's Cloud Speech API. This is generated when you receive credentials for your service account.

Test Connection: Click to be sure Bright Pattern Contact Center can connect to your Google synchronous STT account.

Google Streaming Properties

Google Streaming Speech to Text can be used for both Conversational IVR and call transcription. In the Properties dialog, enter the credentials of your Google streaming STT instance as follows. This allows Bright Pattern to access your STT resource and use it in interactions.

Google Streaming STT integration account properties.

Name: The unique name of this integration account (any)

Type: By default, “Google Streaming STT” because you selected this type when adding the account.

Credentials: Click the upload link to upload credentials.

Default Account: Select the checkbox to mark an account as the default. Only one Streaming STT can be marked as the default account. Services with the transcription option enabled will be transcribed by the default account.

Test Connection: Click to be sure Bright Pattern Contact Center can connect to your Google Streaming STT account.

Watson Properties

In the Properties dialog, enter the credentials for your IBM Watson STT instance as follows. This allows Bright Pattern to access your STT resource and use it in interactions.

Watson integration account properties.

Name: The name of this integration account.

Type: By default, “Watson” because you selected this type when adding the account.

URL: Websocket prefix + your IBM Speech to Text URL in the following format:

For example:

wss://api.us-south.speech-to-text.watson.cloud.ibm.com/instances/1a23456f-121d-4c52-bc06-62168f5a18de

You can find the URL in your IBM Speech to Text service credentials. Note that STT integration uses the secure WebSocket protocol (i.e., "wss"), so only the wss:// prefix is allowed.

Speech detector sensitivity: This setting ranges from 0.0 to 1.0, where 0.0 suppresses all audio and 1.0 suppresses no audio. All tenants with access to edit integration accounts can modify this setting. Non-speech events like coughing and music are filtered.

Background audio suppression: This setting ranges from 0.0 to 1.0, where 0.0 provides no background audio suppression, and 1.0 suppresses all background audio. Volume level is used to differentiate background noise from speech.

Custom language model: This setting allows a custom language model to be set for your Speech to Text integration after creating and training a model on IBM Watson. Enter a customization ID in this field to set a custom language model. If a transcriber uses a different custom language model, the system will switch models as well.

Default account: Select the Default account checkbox to enable the STT integration account.

Test Connection: Click to ensure Bright Pattern Contact Center connects to your Watson Speech to Text account.< Previous | Next >

@@ Line 1: / Line 1: @@
-<translate>= Speech To Text Integration (STT) = <!--T:1-->
-Speech To Text (STT) integration allows your contact center to use speech-to-text functionality to transcribe voice calls and save the transcriptions to interaction records. Full-text transcripts are searchable and include sentiment attributes (if Natural Language Understanding is enabled).
-<!--T:2-->
+= Speech To Text Integration (STT) =
-Bright Pattern integrates with STT providers such as IBM Watson, GoVivace, and Google.
+{{NavLink | '''Integration Accounts''' > ''add account'' > '''Speech to Text'''}}
+Speech To Text (STT) integration enables your contact center to use speech-to-text functionality to transcribe voice calls and save the transcriptions to interaction records. Full-text transcripts are searchable and include sentiment attributes (if Natural Language Understanding is enabled).
-<!--T:3-->
+Bright Pattern integrates with STT providers such as IBM Watson and Google.
-[[File:STT-select.PNG|450px|thumbnail|center|Select the type of STT integration]]
+{{Image450 | STT integration.PNG | Select the type of STT integration.}}
-== Google Properties == <!--T:4-->
+=== Google Synchronous Properties ===
-Google's Cloud Speech API converts audio to text. In the Properties dialog, enter the credentials of your Google synchronous STT instance as follows. This allows Bright Pattern to access your STT resource and use it in interactions.
+Google's Cloud Speech API converts audio to text. Synchronous STT is limited to 1 recordings, making is useful for [[Contact-center-administrator-guide/Concepts/ConversationalIVR | Conversational IVR]] . To transcribe calls, see Streaming STT below. In the Properties dialog, enter the credentials for your Google synchronous STT instance as follows. This allows Bright Pattern to access your STT resource and use it in interactions.
-<!--T:5-->
+{{Note | Google STT requires a payment method to be attached to the account; without this, the STT service would silently not work, and there would be an error in the Google API dashboard.}}
-Please note: Google STT requires a payment method to be attached to the account; without this, the STT service would silently not work, and there would be an error in the Google API dashboard.
-<!--T:6-->
+{{Image650 | Google synchronous STT.PNG | Google Synchronous STT integration account properties.}}
-[[File:Google-STT-Properties-53.PNG|450px|thumbnail|center|Google synchronous STT integration account properties]]
+; Name
+: The unique name for this integration account (any)
-=== Name === <!--T:7-->
+; Type
-The unique name of this integration account (any)
+: By default, “Google synchronous STT” because you selected this type when adding the account.
-=== Type === <!--T:8-->
+; Use enhanced mode
-By default, “Google synchronous STT” because you selected this type when adding the account.
+: When enabled, '''Use enhanced mode''' allows you to use the Cloud Speech APIs [https://cloud.google.com/speech-to-text/docs/enhanced-models enhanced model for phone calls]. This setting allows for more accurate transcriptions of voice calls on [[Tutorials-for-admins/Voice/ConversationalIVRConfiguration|conversational IVR scenarios]]. Enhanced mode is enabled when initializing Google Speech-to-Text.
-=== URL === <!--T:9-->
+; URL
-By default, https://speech.googleapis.com/v1/
+: By default, https://speech.googleapis.com/v1/
-=== API key === <!--T:10-->
+; API key
-The service key ID that is used to authenticate Google's Cloud Speech API. This is generated when you get credentials for your service account.
+The service key ID that is used to authenticate Google's Cloud Speech API. This is generated when you receive credentials for your service account.
+; Test Connection
+: Click to be sure Bright Pattern Contact Center can connect to your Google synchronous STT account.
-== GoVivace Properties == <!--T:11-->
+=== Google Streaming Properties ===
-In the Properties dialog, enter the credentials of your GoVivace STT instance as follows. This allows Bright Pattern to access your STT resource and use it in interactions.
+Google Streaming Speech to Text can be used for both [[Contact-center-administrator-guide/Concepts/ConversationalIVR | Conversational IVR]] and call transcription.
+In the Properties dialog, enter the credentials of your Google streaming STT instance as follows. This allows Bright Pattern to access your STT resource and use it in interactions.
+{{Image650 | Google Streaming STT 2.PNG | Google Streaming STT integration account properties.}}
-<!--T:12-->
+; Name
-[[File:Integration-Account-GoVivace-Properties-51.PNG|450px|thumbnail|center|GoVivace integration account properties]]
+: The unique name of this integration account (any)
+; Type
+: By default, “Google Streaming STT” because you selected this type when adding the account.
-=== Name === <!--T:13-->
+; Credentials
-The unique name of this integration account (any). Because you can have multiple integration accounts of the same type, it is helpful to have a descriptive, memorable name.
+: Click the upload link to upload credentials.
-=== URL === <!--T:14-->
+; Default Account
-By default, wss://services.govivace.com/telephony
+: Select the checkbox to mark an account as the default. Only one Streaming STT can be marked as the default account. Services with the transcription option enabled will be transcribed by the default account.
-<!--T:15-->
+; Test Connection
-STT integration uses the secure WebSocket protocol (i.e., "wss"), so only the ''wss://'' prefix is allowed.
+: Click to be sure Bright Pattern Contact Center can connect to your Google Streaming STT account.
-=== API Key === <!--T:16-->
+== Watson Properties ==
-The GoVivace API key
+In the Properties dialog, enter the credentials for your IBM Watson STT instance as follows. This allows Bright Pattern to access your STT resource and use it in interactions.
-=== Default account === <!--T:17-->
+{{Image650 | Watson STT 2.PNG | Watson integration account properties.}}
-Select the ''Default account'' checkbox if this integration account is to be the default STT integration account.
+; Name
+: The name of this integration account.
-== Watson Properties == <!--T:18-->
+; Type
-In the Properties dialog, enter the credentials of your IBM Watson STT instance as follows. This allows Bright Pattern to access your STT resource and use it in interactions.
+: By default, “Watson” because you selected this type when adding the account.
+; URL
+: Websocket prefix + your IBM Speech to Text URL in the following format:
-<!--T:19-->
+: For example:
-[[File:STT-Watson-Integration-5312.png.png|450px|thumbnail|center|Watson integration account properties]]
+::'''wss://api.us-south.speech-to-text.watson.cloud.ibm.com/instances/1a23456f-121d-4c52-bc06-62168f5a18de'''
-=== Name === <!--T:20-->
+: You can find the URL in your IBM Speech to Text service credentials. Note that STT integration uses the secure WebSocket protocol (i.e., "wss"), so only the wss:// prefix is allowed.
-The unique name of this integration account (any).
-=== Type === <!--T:21-->
+; Speech detector sensitivity
-By default, “Watson” because you selected this type when adding the account.
+: This setting ranges from 0.0 to 1.0, where 0.0 suppresses all audio and 1.0 suppresses no audio. All tenants with access to edit integration accounts can modify this setting. Non-speech events like coughing and music are filtered.
-=== URL === <!--T:22-->
+; Background audio suppression
-Websocket prefix + your IBM Speech to Text URL. You can find the URL in your IBM Speech to Text service credentials.
+: This setting ranges from 0.0 to 1.0, where 0.0 provides no background audio suppression, and 1.0 suppresses all background audio. Volume level is used to differentiate background noise from speech.
-<!--T:23-->
+; Custom language model
-For example: wss://api.us-south.speech-to-text.watson.cloud.ibm.com/instances/1a23456f-121d-4c52-bc06-62168f5a18de
+: This setting allows a custom language model to be set for your Speech to Text integration after creating and training a model on [https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-languageUse IBM Watson]. Enter a customization ID in this field to set a custom language model. If a transcriber uses a different custom language model, the system will switch models as well.
-<!--T:24-->
+; Default account
-Note that STT integration uses the secure WebSocket protocol (i.e., "wss"), so only the ''wss://'' prefix is allowed.
+: Select the ''Default account'' checkbox to enable the STT integration account.
-=== Authentication method === <!--T:25-->
+; Test Connection
-=== API key ===
+: Click to ensure Bright Pattern Contact Center connects to your Watson Speech to Text account.
-The API key (string) for the service instance in your IBM Speech to Text resource, which is used for making secure, authenticated requests.
-<!--T:26-->
-You can find your API key on IBM Cloud by going to your Speech to Text service credentials.
-=== username/password (legacy) === <!--T:27-->
-'''Please note:''' This option is deprecated as of Bright Pattern Contact Center version 5.3.12. For authentication, you must use '''API key''' (see above).
-<!--T:28-->
-The ''username'' and ''password'' are the username (string) and password (string) that were originally used to authenticate IBM's Speech to Text service APIs. The username and password were previously provided in the service credentials for the service instance. We refer to username/password authentication as "legacy" because IBM does not support this method of authentication, as of
-October 30, 2019. IBM now supports only IAM authentication (API key). You can learn more about IAM authentication at [https://cloud.ibm.com/docs IBM Cloud Docs].
-=== Default account === <!--T:29-->
-Select the ''Default account'' checkbox if this integration account is to be the default STT integration account.
-</translate>

Navigation menu

Latest revision as of 04:01, 29 May 2024

Speech To Text Integration (STT)

Google Synchronous Properties

Google Streaming Properties

Watson Properties

Contentsto top