Introduction
This guide covers how admins configure and customize Accent Translation settings in the Sanas Portal, including inference mode, outgoing and incoming audio access, enhancement modes, voice activity detection, and voice profile locking. These controls shape how Accent Translation works for App Users and agents during calls.
Before You Begin
Admins of the Sanas Portal go through the same onboarding process, in preparation for management and supervision of Sanas products — in this case, Accent Translation.
Refer to our Onboarding Guide for the complete walkthrough.
For overall administration of the Sanas Portal, visit these articles:
Product Settings Configuration
Once onboarding is complete and you have setup the account in the Sanas Portal, you can proceed with customizing and setting up controls for Accent Translation. This will shape the overall experience of your users or agents in the Sanas Portal.
How it Works?
From the Sanas Portal, click on Settings.
Under Configuration, look for Products, then Accent Translation.

Note: Sanas products are typically enabled by Sanas admins through Feature Management. If you don't see the section shown above, contact our Support Team for assistance. You can also confirm your organization is subscribed to this product under Subscriptions, accessible at the account level.
Inference Mode
Located under Accent Configuration, account admins can choose to either run the model On-device or via Remote Inferencing.

Note: For more details, please visit Account Settings.
Accent Translation Access
Enable/disable translation independently for Outbound and Inbound audio.

Outgoing Audio
Configure Accent Translation for the audio you send. To utilize this:
Set Source accent and Target accent
Select the Outgoing Accent Translation Model
Choose an Enhancement Mode
Standard for a natural multi-speaker experience (keeps all voices within range), or
Voice Isolation to filter out other voices

Incoming Audio
Configure Accent Translation for the audio you receive. To utilize this:
Select the Incoming Accent Translation Model
Choose Incoming Audio Voice Activity Detection (VAD) Mode
Standard with Ringtone Passthrough to ensure ringtones and hold music play normally without being affected by Accent Translation processing, or
Voice Isolation - General with Ringtone Passthrough (works for all types of microphones while ensuring ringtones and hold music play normally).

Note: By default, Target Accent is set and locked.
Audio Mode When AT Is Off
Choose what audio processing (for example, Noise Cancellation) applies when Accent Translation is toggled off.

Lock Voice Profile Selection
If enabled, enforces a single voice profile (Masculine/Feminine) for users on first activation.

Support
Need help? Get in touch with our Support Team for assistance.