Account Setup and Portal Configuration

Prev Next

Introduction

The Configuration tab (Settings > Configuration) is where administrators control how Sanas behaves for an account or group—from language and accent settings to authentication, desktop app behavior, and subscriptions. This article walks through every section of the Configuration tab so you know what each setting does and where to find it.

Tip: For detailed instructions on a specific feature, see the linked articles throughout.

Configuration settings can be applied at the Account level (organization-wide) or Group level. Select the account or group from the Group Tree on the left before making changes. Most settings include a Lock Configuration toggle. Enable it to prevent subgroup administrators from overriding the setting.

How to get there? Log in to the Sanas Portal, select an Account or Group, then go to Settings > Configuration.

Note: Configuration controls how an enabled feature behaves. To turn a product on or off for a Group, use the neighboring Feature Management tab.


Account Details

Account Information

View and manage the account name, Account ID, and creation date for the selected Account.

Important! Your Account Name, Account ID, as well as Group Names and Group IDs are unique to your organization. Share this information only with authorized individuals on a need-to-know basis (such as your account management team and your agents).


Tags

Add tags to organize this group. Subgroups inherit these tags.

Subscriptions

View all subscribed plans, such as:

  • Accent Translation

  • Speech Enhancement

  • Language Translation

  • Speech Intelligence

Their billing type:

  • Free, or

  • Paid

It also includes:

  • Seat or Minute Allotments, and

  • Subscription Term Dates

How to manage?

Use Add New Subscription to add a plan, or Edit on an existing plan to update seats, minutes, or term dates.


Account Settings

Timezone

Sets the timezone used for timestamps shown to Portal Users (reports, logs, activity). Choose from the Select Timezone dropdown.

Inactive App Users

Automatically deactivates Sanas App users who haven't used the app for a configured number of days, freeing up license seats without manual tracking. This is configured at the Account level only.

Note: See how to setup Automatic Deactivation of Inactive App Users for full setup steps.

Remote Inferencing

Let’s you run Sanas speech models on a remote server instead of the end user’s device. This reduces dependence on local hardware and keeps performance consistent across users.

For each product — Accent Translation, Speech Enhancement, enter the endpoint address of your remote inference service.

Note: The address must be reachable from end-user devices, with network access and permissions configured.


Platform Authentication

Application Authentication

Controls how users log in to the Sanas App. To start, choose one authentication mode from the list below:

Authentication Mode

Description

User Activation Key (UAK)

Users enter a valid UAK-generated by adding them to a Group.

Auto Activation

Users on systems with the Sanas app and a valid installation key get automatic access.

SSO (Single Sign-On)

Users with access through your SSO Provider can access the app directly.

Email-Passcode

Users enter a valid email and passcode.

Google

Users sign in with their Google account.

Portal Authentication

Configure the connection used to authenticate Portal (web) logins for your domain. Add or select an existing SSO connection and view its call status (Enabled/Disabled).


Products

Each product area lets you configure how that Sanas capability processes audio for the selected Group or Account.

Accent Translation

  • Inference Mode

    • Run the model On-device or via Remote Inferencing (see Account Settings above for more details)


  • Accent Translation Access

    • Enable/disable translation independently for Outbound and Inbound audio


  • Outgoing Audio

    • 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 isolate speech to only the nearest voice, suppressing other voices for maximum clarity

        • Auto (automatic adjustment between Nearfield and General based on detected mic type)

        • Nearfield (ideal for headset users when mic is directly at mouth position)

        • General (works for all types of microphones)


  • Incoming Audio

    • Set Target Accent

    • Select the Incoming Accent Translation Model

    • Choose an Incoming Audio Voice Activity Detection (VAD) Mode

      • Voice Isolation for any mic, with ringtone and hold-music passthrough, or

      • Standard for ringtones and hold music pass through untouched by accent translation processing


  • Audio Mode When Accent Translation Is Off

    • Choose what audio processing (for example, Noise Cancellation) applies when Accent Translation is toggled off


  • Lock Voice Profile Selection

    • Enforce a single voice profile (Masculine/Feminine) for users on first activation

Noise Cancellation

Toggle Enable Inbound Noise Cancellation to allow incoming-audio noise cancellation alongside outgoing Accent Translation.

Note: Select the Outgoing and Incoming Noise Cancellation model versions independently (each has a minimum required app version).

Speech Enhancement

  • Inference Mode

    • Run the model On-device or via Remote Inferencing (see Account Settings above for more details)


  • Speech Enhancement Access

    • Enable/disable independently for Outbound and Inbound audio


  • Outgoing Audio

    • Choose an Enhancement Mode

      • Standard for processing audio from the surrounding environment rather than a single speaker, or

      • Voice Isolation for isolating your voice and filters out everything else

        • Auto (automatic adjustment between Nearfield and General based on detected mic type)

        • Nearfield (ideal for headset users when mic is directly at mouth position)

        • General (works for all types of microphones)

    • Select an Outgoing Speech Enhancement Model


  • Incoming Audio

    • Select an Incoming Audio Voice Activity (VAD) Mode

      • Standard, or

      • Standard with ringtone passthrough (keeps ringtones or hold music unaffected by processing)

    • Choose an Incoming Speech Enhancement Model

Language Translation

Configuration

  • Language Settings

    • Sets the default Source Language — what the App User speaks, and Target Language — what the recipient hears translated

      Note: Users can change these selected languages in the Sanas app.

  • Transcription

    • Shows users a real-time transcript of the conversation

  • Incoming Translated Speech

    • When toggled ON, translated speech is turned off for faster turn-taking. The agent reads the translated text and responds verbally.


Custom Glossary

  • Lets you build a list of words and phrases, such as brand or product names, that Sanas keeps in their original form instead of translating.

    Note: You can add terms one by one or in bulk with a CSV upload, export the list, reset it to the inherited defaults.


Custom Translations

  • Set your own translation for specific terms, so that a term in one language always becomes the term you chose in the other, in both directions.

    Note: You can add translations one at a time or in bulk with a CSV upload, search and export the list.


Recordings (this includes debug logging for troubleshooting purposes)

  • Translation Debug Logging

  • LT Recording Transfer

    • Deliver Language Translation transcripts, and optionally audio, to your own Amazon S3 bucket.


Advanced (typically Sanas-Admin use)

  • Display Translation Latency, and

  • Language Translation Audio Crossfade Tuning

    • Once enabled, turns the audio crossfading mixer on for this group's app users

      • Choose a Crossfade Mode

        • Server-side Crossfade (the translation server evens out the caller's voice and lowers it under the translation, most in the speech frequencies, before the audio reaches the app)

        • Client-side Crossfade (the app mixes the caller's voice with the translation on the device)

          • Crossfade In/Out Timing

          • Activity Threshold

          • Low Gain

          • Ducking Level

    Note: Advance Settings are for troubleshooting or demos only, typically for Sanas Admin use.

Speech Intelligence

Configuration

  • Model Selection is used to choose versions for the following models:

    • Speech to Text (STT)

    • Personally Identifiable Information (PII)

    • End of Call (EOC)

    • Ringtone Classifier (RTC)

    • Speaker Diarization (SEM)

  • Outgoing/Incoming Mode

    • Standard (balances clarity for both close and distant voices)

    • Nearfield (close-range mics)

    • Farfield (room mics/speakerphones), or

    • Telephony (phone calls)

  • Call Summary Options has toggles to choose which sections appear in generated call summaries

    • Action Items

    • Discussion Points

    • Compliance Alerts

    • Comments (this is optional)

    Note: Summary, Action Items, and Discussion Points are now configurable under Content Generation (below).


Transcript Management

Configure what percentage of PII-redacted transcripts Sanas retains, for how long, and optionally transfer them to your own destination.

  • Transcript Storage

    • Percentage of calls retained

      • (100%), Every call’s transcript is stored

      • Below 100%, Sanas keeps a random sample of calls spread across the day

      • At 0%, nothing is kept

    • Retention duration

      • Between 1 Day to 365 Days, stored transcripts are permanently deleted after the selected timeframe. A background job runs the deletion, so it can happen up to about 6 hours after the deadline. Deleted transcripts can’t be recovered.

    • Alert Utterance Retention

      • If enabled, the transcript snippets attached to compliance alerts are kept even after the full transcript is deleted. You can still read why an alert fired months later, without keeping whole calls.

  • Transcript Transfer

    • Once enabled, it automatically sends the PII-redacted transcript of every completed call to storage your organization owns. Turn it on with the toggle, then choose a destination. You can pick one you’ve already set up, or create a new one in Amazon S3 or Azure Blob Storage.

  • Live Delivery

    • It streams transcripts in real time to your own HTTPS endpoint, authenticated with OAuth client credentials. It’s separate from Transcript Transfer, which delivers to S3 or Azure storage. Choose whether to remove PII from transcripts before delivery, and whether transcripts go to your endpoint only, Sanas cloud only, or both.

  • Test Datasets

    • They are reusable, PII-redacted sets of transcripts for testing your Speech Intelligence configurations before you roll them out.

      • Dataset Library: upload your own dataset, sample real calls from production, or generate synthetic transcripts

      • Dataset Scripts: saves the setups used to generate datasets, so you can re-run, edit, or archive them later


Content Generation

  • It controls how Speech Intelligence writes each call’s Summary, Action Items, and Discussion Points for a group. Each one starts on Sanas defaults. Use Configure to adjust settings such as length, tone, format, and volume, or Reset to Sanas defaults to undo your changes.


Compliance Alerts

  • It lets you create and manage the alerts that run on your account’s calls, after testing them against the datasets in Transcript Management.

    • Production runs alerts on your production calls, with up to 10 active at once

    • Sanas Library offers ready-made alerts for your industry and call type that you can fork and customize


Conversation Duration

  • It sets the target call length for the Live Tracking supervisor timer, from 30 seconds to 60 minutes.

    • Amber at 80% of the target

    • Red once the call passes the set target length


Desktop App

  • It controls which post-call sections, such as Call Stats, Summary, Action Items, and Compliance Alerts, appear in the Sanas Desktop App and the Agent Web Portal for a group. Turning a section off only hides it; everything is still generated and stored.


Outbound Call Alerts

  • It controls whether compliance alerts run on calls the agent dials out. Turn on Suppress alerts on outbound calls to stop all in-call and post-call alerts on outbound calls for the group.

    Note: Inbound calls, and calls whose direction is unknown, still get alerts as usual.


Industry & Call Type

  • Lets you tag a group with an Industry Type (such as Logistics, Healthcare, or Financial) and a Call Type (such as Collections, Fraud, or Customer Service) from a predefined catalog.

    Note: Downstream Speech Intelligence modules use this combination for defaults and filtering.


PII Configuration

  • Toggle which PII categories the on-device redactor applies for this group. Sub-groups inherit these choices and can change anything you have not locked. These includes:

    • Personal: Name, Date of Birth, Phone Number, Email, Address, P.O Box, Place, Zip Code

    • Government IDs: SSN, Passport, Driving License, State Real ID

    • ID: ID Number, Tracking Number, Case Number, Invoice Number

    • Financial: Credit Card Number, Credit Card CVV, Currency, Crypto Information, Bank Account Number

    • Authentication: Password, PIN

    • Other: Vehicle VIN, IP Address

    Note: All categories are redacted by default. Turning one OFF will display these items in clear text on the next call.


Custom Glossary

  • Use Custom Glossary

    Once enabled, activates the added terms, allowing Speech Intelligence models to recognize and transcribe them correctly.

  • Redaction Terms

    Mark customer terms for redaction with a tag such as MEDICAL or ORG.

    Note: One tag per line: TAG then the term. Redaction applies to new calls after the engine picks up the glossary. Calls already stored are not changed.


Desktop Application

Application Version & Update Preferences

Application Version

  • Controls which Sanas App version is deployed. By default, users automatically receive the latest version, or you can pin a specific Application Version instead.


Auto Update Preferences

  • Auto update is now configurable per account, so administrators control how and when the app updates.

    • Grace Period - once selected, admins can choose from 1 to 5 days before the update enforced to the app. By default, the range is set to 5 days.

    • Immediate - once selected, the user receives a 10-minute warning before the update begins.


Download Preferences

  • To add a schedule when the app can be updated, look for Download Preferences on the same section.

  • If needed, apply bandwidth throttling by checking the Would you like to configure bandwidth throttle? box. Option between 100kbps, 200kbps, and 300kbps is available, with a default setting set to 100kbps.

    Note: Download Preferences settings are always followed, regardless of the Auto Update preference selected.


Enable Auto Update

  • In order for the auto update preferences to work, toggle on Automatically update to the selected app version.

    Note: Turning it off stops users who haven't started the update from receiving it; those who already downloaded it or started the install countdown will still complete installation.

Application Settings

Hear Your Voice

  • Lets users preview how their voice sounds with Sanas on


Pause Sanas Inbound Processing

  • Pauses inbound processing for the selected duration (5, 10, or 15 seconds) so notifications and alerts can be heard clearly. When disabled, some notification and alert sounds may be missed.


Add Comfort Noise

  • Adds a low bed of background sound to Sanas output so the line is never completely silent.

    Noise Type

    1. White Noise - Generated in real time and shaped to blend naturally with the agent’s voice and environment.

    2. Ambient Noise - A looped recording of contact-center ambience played beneath the call at a fixed level.

    Noise Level

    1. Subtle: 15%

    2. Balanced: 25% (Default)

    3. Strong: 35%

    4. Maximum: 50%

    Note: The toggle is disabled by default. When enabled, it starts with White Noise at the Balanced level.


Sanas Personalization

  • A process of preserving a user's natural voice traits during translation is also configured from this area.

  • The script used to personalize your voice profile can now be customized, and set per account, matching the wording to your language and style.

    Note: If no custom script is configured, the default script is shown. See Personalize your voice profile for more details.


Allow Users to Toggle Products

  • When enabled, lets users enable or disable Sanas products in the app.


Sanas Widget

  • Allow users to turn Sanas products on or off directly from the widget without opening the full application.


Microphone Stream

  • Automatically pauses the microphone stream when no call is active, and resumes it once a call is detected.

    Note: This setting is accessible to Sanas Admins only.

Sanas Audio Settings

Sanas as Default Microphone/Speaker for OS

  • Sets Sanas as the system-level default device.


Mute Sanas Speaker/Microphone

  • Lets users temporarily mute the Sanas speaker/microphone during calls.

    Note: This setting is accessible to Sanas Admins only.


Automatic Volume Optimization (AVO)

  • Automatically adjusts microphone volume for optimal conversations.

    Note: Turning this feature on sets Microphone Volume Adjustment to Flexible volume control.


Enable Microphone/Speaker Volume Adjustment for App Users

  • When disabled, App Users cannot adjust the Sanas Microphone/Speaker volume, which remains fixed at 100%.

    • Sync with selected Microphone/Speaker

      • If Sync with selected Microphone is selected, it turns Automatic Volume Optimization OFF.

    • Flexible Volume Control

    Note: This setting is accessible to Sanas Admins only.

Early Access

Toggle Enable early access to new features and models to let users on this Group/Account try upcoming (beta) features and models before general availability.

Troubleshooting & Logging

Troubleshooting & Logging

Control the troubleshooting tools available in the desktop app for this group.

  • Advanced Troubleshooting Menu

    Adds an advanced troubleshooting menu to the desktop app so users can run guided checks with Sanas Support.


Report a Problem

Users can always report a problem from the desktop app. Choose what a report is allowed to include.

  • Record a Voice Sample

    Lets users attach a short voice recording to a report for Sanas to review and reproduce audio issues. Switch it OFF and Report a Problem still works, just without the recording option.


Authentication

SSO Settings

Add or manage SSO (Single Sign-On) connections used to authenticate access to this Account/Group. Shows connection status (for example, "No SSO connections" until one is added).

Note: Refer to this article for details on how to configure SSO for your account.


Danger Zone

Delete Account

Permanently deletes the Account.

Warning! This action cannot be undone — use with caution and only when certain.


Support

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