Configure Speech Enhancement Modes

Introduction

Sanas Speech Enhancement (SE) features built-in enhancement modes that enable you to optimize audio performance in various use-case scenarios. This article describes each mode and explains how to configure them.

Enhancement Modes

• Standard - A multi-speaker mode that preserves background human speech while canceling environmental noises. Recommended for shared workstations and open-desk setups.

• Voice Isolation - A single-speaker mode that preserves only the primary speaker's voice while canceling distant human speech and environmental noise. Recommended for agents using a headset or personal microphone.

Voice Isolation includes the following sub-modes:

Note: Standard is the default enhancement mode for SE.

Before you begin

• Ensure your Portal role has Group or Account Settings: Full Access permissions to modify the configuration.

Configure the enhancement mode

1. Log in to the Sanas Portal using your credentials.

2. On the Group Tree, select the Group you want to configure. To apply the configuration across all Groups, select your Sanas Account instead.

3. Navigate to Settings > Configuration > Speech Enhancement.

4. Select an enhancement mode:

   • Standard — For multi-speaker environments.

   • Voice Isolation — For single-speaker environments. Select the appropriate sub-mode based on the agent's microphone setup:

     • Auto — Headset type is detected automatically.

     • Headset mic — Agent uses a headset with a boom microphone.

     • Built-in mic — Agent uses a laptop's built-in microphone or a headset without a boom microphone.
       

5. Select your preferred Speech AI model from the respective drop-down menu of your selected enhanced mode. Sanas selects the recommended model automatically.

6. Click Save. The updated mode applies to all agents in the selected Group.

Support