Deploying and configuring Speechmatics transcription

The Speechmatics transcription is considered a 3rd party transcription engine, which requires using a separate on-premise or cloud based Speechmtaics infrastructure to run the transcription service. The Verba Speech Analytics Service is connecting to the Speechmatics platform and sends audio files for transcription. For more information see Deploying transcription.

The Speechmatics integration requires the Speechmatics API 1.0.

Once, the Speecmatics platform is available, the required Data Processor has to be created to enable the integration with the Speechmatics transcription engine. Follow the steps described in Configuring and running transcription to create the processor and select the Speechmatics engine. The following table describes the settings available for a Speechmatics data processor:

Configuration item	Description
Name	Name of the data processor. This name will identify this processor across the system.
Type	Select Speech Transcription
Engine	Select Speechmatics
API Root URL	URL of the Speechmatics API (on-prem server or cloud)
API User	Speechmatics API user name
API Token	Speechmatics API token
Enable Speaker Diarization	Allows separating participants in conversations and producing a dialog like output

After creating the data processor, you can follow the guidelines at Configuring and running transcription to configure one or more data management policies.

License requirements

The Speechmatics transcription engine does not require specific licenses, only the Advanced Archive license is required to enable the integration. Please contact your Verint sales representative for more information.

Although there is no specific license requirement, the feature requires a license to be assigned to users through the role configuration. The following permission(s) are required for the Speechmatics speech transcription:

Transcribe Conversations (3rd Party)

Uploading new ASR models

Please contact Speechmatics for more information.

Customizing the Speechmatics ASR models

Please contact Speechmatics for more information.