Trunking Recorder Call Speech-to-text
Call Speech-to-text enables some recorded calls to be transcribed using the Microsoft Azure Speech services. Currently, only calls that trigger a Call notification email will be transcribed.
The Speech-to-text feature does requires a Azure Cognitive Services subscription.
Free (F0) subscriptions currently offers 5 audio hours free per month.
Paid standard (S0) subscriptions cost roughly $1 per audio hour.
To verify currently pricing check Azure for more information.
Note: Azure requires WAV files, when recording Unitrunker calls as MP3 files a WAV file will also be recorded automatically. If importing Calls from SDRTrunk as MP3 files they will automatically be converted to WAV as needed. All WAV files will be deleted once Call Notification is complete.
To enable Call Speech-to-text:
- Create and setup an Azure subscription.
- Create the Speech resource in Azure generating the Azure Key and Region information. See Azure Speech setup for more information.
- From the Configure menu select the "Advanced" tab.
- Check the "Enable Call Speech-to-text" checkbox
- Enter your Azure subscription key that you generated on the Azure portal website.
- Enter your Azure region information as displayed on the Azure portal website.
- Enter any extra Keyword phrases you need to help improve accuracy of the speech recognition. After a few calls have been processed you will start to notice if extra phrases are needed.
- Click the "Save" button, Trunking Recorder will attempt to verify that the Microsoft Visual C++ 2019 Redistributable 64-bit is installed. If not it will display a message allowing you to download the file from Microsoft.
- Install the Microsoft Visual C++ 2019 Redistributable 64-bit if you were prompted.
- If configured correctly all new Call notification emails will include the transcribed call text in the email.
- If any errors are encountered they will be logged in the Trunking Recorder log file.
