/
Quality Analysis with AWS Account

Quality Analysis with AWS Account

Overview

Starting with version 3.40.0, a redesigned graphical user interface (GUI) has been introduced to enhance the user experience in the Voice Recordings section.
This update is part of the New Client Experience.

In the New Client Experience, users can perform Quality Analysis on voice recordings using AI-powered tools provided by Amazon AWS. The following analysis features are available:

  • Transcription – Converts audio recordings into text.

  • Sentiment Analysis – Identifies emotional tone within the conversation.

  • Post-Call Analytics – Provides detailed sentiment trends and agent-customer interaction insights over time.

To launch any of the AI features:

  1. Navigate to the Voice Recordings section.

  2. Select one or more recordings.

  3. Use the action icons in the top-right corner of the interface to run:

    • Transcribe

    • Sentiment Analysis

    • Post-Call Analytics

  4. To export data, use the Export button to download results in .csv format.


Each voice recording may support multiple transcriptions, sentiment analyses, and post-call analytics, depending on user permissions.

image-20240917-074425.png

You can select multiple voice recordings and run analysis actions (Transcribe, Sentiment Analysis, or Post-Call Analytics) simultaneously.
Note: The availability of each action depends on the specific permissions associated with each recording. Not all actions may be enabled for every recording.
To view the available actions for a specific recording click the three-dot menu next to the audio file and only the actions you have permission for will be shown.

To review the analysis results for a specific recording:

  1. Click Edit on the desired voice recording.

  2. The Edit Voice Recording page displays:

    • Recording details (read-only)

    • Playback controls (play, rewind, forward)

    • Options to download the file or launch AI actions

  3. You can assign a rating to the recording from this interface.

The Transcribe, Sentiment Analysis, and Post-Call Analytics tabs and buttons will only appear if these features are enabled on your license and under: Settings → General → Quality Analysis

image-20241015-104719.png

Requirements

To enable Quality Analysis features in XCALLY, follow the steps below to properly configure your Amazon AWS account and system environment.

  • Request the XCALLY Quality Analysis add-on license.

  • Create an Amazon AWS Account with an IAM user configured for the necessary services.

  • Create and configure IAM User:

    • Go to AWS Console → IAM → Users.

    • Select your IAM username.

    • Navigate to the Permissions tab and click Add permissions.

    • Choose Attach policies directly, and select the following AWS modules:

  • You must create an S3 bucket to store audio files and analysis results.

    • From the AWS Console Home, navigate to S3 → Buckets

    • Create a new bucket and select your desired AWS region. Refer to the Amazon S3 User Guide for detailed steps.

  • Ensure that the IAM user has write access to both Objects and Bucket ACLs in the S3 bucket's permissions settings.

  • Starting from XCALLY version 3.35.0, the installation script .env requires specific environment variables to support Quality Analysis via Redis container. Add the following entries to your .env file during installation or update:

XC_QA_QUEUE_WORKERS=10 # Quality Analysis SECTION XC_QA_REDIS_PORT=21000 # timings redis port XC_QA_REDIS_DB=0 # timings redis db XC_QA_REDIS_USERNAME= XC_QA_REDIS_PASSWORD= XC_QA_REMOVE_FAILED_JOBS_AFTER=3600 # 1 hour XC_QA_REMOVE_COMPLETED_JOBS_AFTER=604800 # 7 days

Refer to the Troubleshooting section to verify whether the required Redis container is running correctly.

  • To run Transcription or Post-Call Analytics, make sure the Split Voice Recordings option is enabled:

    • Go to Settings → General.

    • Enable Audio Split for Voice Recordings.

Video Tutorial

https://app.guidde.com/share/playbooks/jn8iHEYVN8nrrHqz73szqr?origin=3wPlti10dEfOGQjG7BKQvB2q4IC3

The video tutorial provides a comprehensive walkthrough of all Quality Analysis features.

Please be aware that Post-Call Analytics and QA Categories are available exclusively when using Amazon AWS as the cloud provider.

 

 

XCALLY Configuration

To enable Quality Analysis features using Amazon AWS, follow these steps to configure the cloud provider in XCALLY.

Navigate to XCALLY Tools to add a Cloud Provider Account

image-20250331-064327.png

  • Click the Add button to create a new cloud provider account.

  • Fill in the required fields:

    • Name – A custom label for the account (e.g. AWS Account).

    • Service – Select AmazonAWS from the dropdown.

    • Access Key ID

    • Secret Access Key

image-20250617-094943.png

 

To obtain your Access Key ID and Secret Access Key from AWS:

  1. Sign in to the AWS Management Console.

  2. Go to IAM → Users → [your username] → Security Credentials.

Under Access Keys, either:

  • View an existing key (if available), or

  • Click Create Access Key to generate a new one.

The system asks you to choose an “access key best practices & alternatives”: you can select Third-party service and then you can Retrieve your access key

Be sure to copy and securely store the Secret Access Key before clicking Done. It will not be displayed again.

 

  • To use Post-Call Analytics, you must enable audio splitting:

    • Go to Settings → General → Global.

    • Enable the Split Voice Recordings option.

This setting ensures separate audio channels for each speaker, which is required for accurate sentiment and post-call analysis.

image-20240523-072449.png

  • Configure Quality Analysis Settings

    • Navigate to Settings → General → Quality Analysis.

    • Configure the following options:

      • Select the default language to be used for audio transcriptions. Refer to the list of supported languages and features for Amazon Transcribe.

      • Enter the name of the Amazon S3 bucket you previously created.
        This bucket will be used to store files and results related to Transcription, Sentiment Analysis and Post call analytics

image-20250221-111414.png

  • In the Quality Analysis settings, configure the features you want to use:

image-20250221-111522.png

Enable Transcribe, Sentiment Analysis and Post call analytics.

Region: select the AWS Region closest to your location from the provided list.

Ensure that the selected region matches the region used in your AWS S3 bucket configuration.
The S3 URI must point to the correct AWS region for successful integration

Account: choose one of the previously configured cloud provider accounts (e.g., your AWS account).

 

Quality Analysis on Old Experience

Quality Analysis features can be accessed from the following sections:

Transcribe

To use Amazon AWS as the default provider for transcriptions:

  1. Go to Settings → General → Quality Analysis.

  2. In the Transcribe configuration section, select your AWS account as the default.

  3. Amazon Transcribe is supported in the following AWS Regions

image-20250423-101236.png

Navigate to the Voice Recordings section. Click on the Transcribe icon for the desired call.

 A modal window will open with:

  • The default account pre-selected (as defined in settings).

  • Options to select Region and Language for the transcription.

image-20250423-101535.png

 

You can change the selected account in the modal (e.g., to use a different provider for better language support). Changing the account here will not affect the global default account in the settings.

Click Start Transcription. The system will:

  • Upload the audio file to the configured AWS S3 bucket (technically your audio is sent to a bucket configured on AWS)

  • Trigger Amazon Transcribe to process the file and generate the transcript (when AWS is ready, it takes the audio from the bucket and launches the transcription).

Once transcription is complete, open the Edit Voice Recording page to access the transcript.

image-20250423-102109.png
image-20250423-102645.png

 

  • Record: original call recording in mono format.
    If split voice recording is enabled, a stereo version with separate channels for each speaker is created.

  • Transcription: The conversation is transcribed and, if audio splitting is enabled, each speaker’s dialogue appears on a separate line. Amazon Transcribe uses machine learning models to convert speech to text.

Transcript feature:

  1. Download icon: download individual speaker audio files.

  2. Mute icon (avatar): click on the avatar icon to mute the single-speaker audio.

Sentiment Analysis

Sentiment Analysis evaluates the emotional tone of a conversation based on the call transcript. It classifies prevailing sentiment into one of the following categories, with corresponding confidence levels expressed in percentage:

  • Positive – Generally optimistic or favorable tone

  • Negative – Generally unfavorable or critical tone

  • Mixed – Contains both positive and negative sentiment

  • Neutral – Objective or emotionless tone

Sentiment Analysis can only be performed on completed transcriptions. Ensure the transcription process is finished before launching the analysis.

You can initiate Sentiment Analysis from the following sections:

To use Amazon AWS by default for Sentiment Analysis:

  1. Navigate to Settings → General → Quality Analysis.

  2. Under the Sentiment Analysis section, select your AWS account.

  3. Sentiment Analysis (Amazon Comprehend) is supported in the following AWS Regions

  • In the Voice Recordings list, click the three-dot menu beside a recording and select Run Sentiment Analysis

image-20250423-095516.png

  1. A modal will appear with the default account, region, and language pre-filled.

image-20250423-103134.png

 

You can change the selected account in the modal (e.g., to use a different provider for better language support). Changing the account here will not affect the global default account in the settings.

Once the analysis is complete, navigate to the Edit Voice Recording page and open the Sentiment Analysis tab. You will see:

Sentiment Analysis

 

  • Sentiment (Primary Result): The overall sentiment determined with the highest confidence (POSITIVE, NEUTRAL, MIXED, or NEGATIVE) .

  • Confidence Scores: A breakdown of confidence levels (%) for each sentiment category.

For more technical details, refer to the Amazon Comprehend API: DetectSentiment documentation.

 

Post-Call Analytics

Post-Call Analytics provides a more granular evaluation of sentiment trends throughout the call. It helps assess how both the customer and agent felt during different stages of the interaction.

Post-Call Analytics is supported in the following AWS Regions

From the Voice Recordings section, click the three-dot menu next to a recording and select Run Post call Analytics.
Choose the Account, Region and Language and start the analysis

Post call Analytics
Post call Analytics

Open the Edit Voice Recording page and navigate to the Post-Call Analytics tab. The following visualizations and data will be available:

  • Call overall sentiment score per speaker, with a range from 0 to 5. This metric can help identify if your agent is able to delight an upset customer by the time the call ends.

  • Sentiment Time Graph: displays sentiment scores per speaker across four quarters of the call (range:-5 to +5).

XCALLY normalizes the AWS sentiment scale as follows:

  • AWS -5 → XCALLY 0

  • AWS 0 → XCALLY 2.5

  • AWS +5 → XCALLY 5

 

For more details, refer to the https://docs.aws.amazon.com/transcribe/latest/dg/call-analytics-batch.html

Quality Analysis on New Client Experience

When using Amazon Web Services (AWS) as your provider, you can run the following AI-powered features in XCALLY: transcription, sentiment analysis and post-call analytics features.

These are accessible from:

Transcribe

To use Amazon AWS as the default provider for transcriptions:

  1. Go to Settings → General → Quality Analysis.

  2. In the Transcribe configuration section, select your AWS account as the default.

image-20250423-101236.png

To run a transcription:

  1. Go to Voice → Recordings.

  2. Click the three dots next to a recording and select Run Transcribe.

image-20250417-121530.png

  1. A modal opens showing the default account

  2. If AWS is selected, choose the Region and Language from the dropdown

image-20250418-100909.png

You can change the selected account in the modal (e.g., to use a different provider for better language support). Changing the account here will not affect the global default account in the settings.

Click Start Transcription. So the audio file is uploaded to the configured AWS S3 bucket → AWS processes the file and returns the transcript.

Click the three dots → View to see the transcription:

image-20250310-101639.png

  • Two audio bars, indicating the User and Customer audio channels (enabling split voice recordings in settings section). Dual audio waveforms (agent = downward; customer = upward).

  • Controls to play, rewind, fast-forward and download audio

  • Transcribed conversation with:

    • speaker role,

    • timestamp (begin at and duration time reported in seconds)

    • Word-level confidence colors: label to indicate the speech recognition's reliability level of transcribe. Black > 90%, yellow ≈ 50%, red < 50% (the system had difficulty identifying the correct words).

    • A red dot to identify the part of conversation played

Confidence color is visible only if you use AWS as provider for Transcription.

 

In Transcribe tab, you can see the details of each transcription:

image-20241016-083255.png

 

  • Created at (default descending sorting and filter from calendar)

  • Status (with checkbox menu)

    • New: job created, waiting to process

    • UploadingData: file being uploaded

    • InProgress: transcription runnin

    • Unknown: error or undefined status

    • Completed: transcription successful

    • Failed: transcription failed (warning icon shows error message, if available)

  • Service: Amazon AWS or OpenAI

  • Language, selected language code

  • View the transcription.

Sentiment Analysis

Sentiment analysis can only run after a transcription is completed. AWS must be configured with region and language.

  • Click the three dots on a recording and choose Run Sentiment Analysis.

  • In the modal, the default AWS account appears: select region and language.

  • Click Start to initiate analysis.