Introduction
As a Portal Admin, this article walks you through configuring Sanas products for your organization, with a focus on Speech Intelligence — a real-time speech analytics solution that transcribes calls on-device, redacts PII, and delivers call summaries and compliance alerts.
This guide covers the key settings in the Sanas Portal: model selection, audio processing modes, transcript storage and transfer, test datasets, industry and call type tagging, and custom glossary setup. With these configured, App Users benefit from automated transcription, PII protection, and ready-made call summaries — freeing them from manual note-taking so they can focus on the conversation.
Before You Begin
Speech Intelligence is a standalone product that also works alongside other Sanas products, such as Accent Translation, Speech Enhancement, and Language Translation. When you subscribe to Speech Intelligence, Sanas will configure it for your organization within the Sanas App and Portal.
By that point, Portal Admins should already have completed onboarding the aforementioned products, with additional steps now added to onboard Speech Intelligence as well.
Refer to our Onboarding Guide to revisit the initial walkthrough.
For an overall administration of the Sanas Portal, visit these articles:
Note: This article focuses on the Sanas Portal configuration that controls the user's experience in the Sanas App. For content regarding the Speech Intelligence interactive dashboard, refer to this link.
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 Speech Intelligence. 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 Speech Intelligence.
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.
Configuration
Model Selection
Option to select the appropriate models for the following component of Speech Intelligence:
Speech to Text Model (STT)
Personally Identifiable Information Model (PII)
End of Call Model (EOC)
Note: The STT model requires Sanas App version 5.9.0 or later, while the PII and EOC models require version 5.5.5 or later.
Outgoing Mode
Lets you choose the audio processing profile applied to the outgoing voice of your App Users, based on the type of microphone or call setup they're using.
Incoming Mode
Determines the audio processing profile applied to your customer or recipient’s voice on the call.
Call Summary Options
Enable the toggles for the sections you want to appear in generated call summaries in the Sanas app.
Transcript Management
Configure what percentage of PII-redacted transcripts Sanas retains, for how long, and optionally transfer them to your own destination.
Transcript Storage
Controls how long and how much call transcript data is retained.
Percentage slider determines what portion of calls have their transcripts saved. At 0%, no transcripts are retained; at 100%, every call is retained.
Retention Duration dropdown specifies how long transcripts are kept before deletion. After the selected period, transcripts are automatically hard-deleted by a background job (with up to ~6 hours of delay past the deadline), and this deletion is irreversible. Select an option from 1 day to 365 days.
Alert Utterance Retention toggle when enabled, lets you preserve transcript snippets tied to compliance alerts even after call transcript is deleted, so the alert details remain readable/reviewable later.
Transcript Transfer
When enabled, delivers every completed call's redacted transcript in real time to an external destination.
Test Datasets
Provides reusable, PII-redacted transcript datasets for testing Speech Intelligence configurations before applying them to live calls.
Dataset Library
Build Dataset through the following:
Upload Dataset
Sample from Production
Generate Synthetic
Dataset Scripts
Contains the list of datasets created for testing.
Conversation Duration
Sets the target conversation duration for the Live Tracking supervisor timer.
Target Duration
Define the Target Duration for Live Tracking supervisor timer in MM:SS format.
Note: The timer only accepts durations between 00:30 and 60:00. An amber alert triggers at 80% of the target duration, and a red alert triggers once the target is exceeded.
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.
Industry Type & Call Type
Select from the dropdown of Industry Type and Call Type.
Note: Downstream Speech Intelligence modules use this combination for defaults and filtering.
Custom Glossary
Account admins can define customer-specific names and terms — brands, people, places, or domain jargon — that Speech Intelligence should recognize and transcribe correctly.
Custom Glossary
Enabling the Use Custom Glossary toggle activates the added terms, allowing Speech Intelligence models to recognize and transcribe them correctly.
To add the glossary terms:
Enter the words manually, separated by commas, or
Bulk upload them through .txt format.
Support
Need help? Get in touch with our Support Team for assistance.