Analyzing call center audio with Call Analytics
Use Amazon Transcribe Call Analytics to gain insight into customer-agent interactions. Call Analytics is designed specifically for call center audio and automatically provides you with valuable data relating to each call and each participant. You can also hone in on data at specific points throughout call. For example, you can compare customer sentiment in a call's first few seconds to the last quarter of the call to see if your agent provided a positive experience. Other use case examples are listed in the following section.
Call Analytics is available for post-call and real-time transcriptions. If you're transcribing a file located in an Amazon S3 bucket, you're performing a post-call transcription. If you're transcribing an audio stream, you're performing a real-time transcription. These two transcription methods offer different Call Analytics insights and features. For more detail on each method, see Post-call analytics and Real-time Call Analytics.
With real-time Call Analytics transcriptions, you can also include post-call analytics in your request. Your post-call analytics transcript is stored in the Amazon S3 bucket that you specify in your request. Refer to Post-call analytics with real-time transcriptions for more information.
API operations specific to Call Analytics
Post-call: CreateCallAnalyticsCategory,
DeleteCallAnalyticsCategory,
DeleteCallAnalyticsJob,
GetCallAnalyticsCategory,
GetCallAnalyticsJob,
ListCallAnalyticsCategories,
ListCallAnalyticsJobs,
StartCallAnalyticsJob,
UpdateCallAnalyticsCategory
Real-time: StartCallAnalyticsStreamTranscription, StartCallAnalyticsStreamTranscriptionWebSocket
Common use cases
Post-call transcriptions:
-
Monitor issue frequency over time: Use call categorization to identify recurring keywords within your transcripts.
-
Gain insight into your customer service experience: Use call characteristics (non-talk time, talk time, interruptions, voice loudness, talk speed) and sentiment analysis to determine if customer issues are being appropriately resolved during the call.
-
Ensure regulatory compliance or adherence to company policy: Set keywords and phrases for company-specific greetings or disclaimers to verify that your agents are meeting regulatory requirements.
-
Improve handling of customers' personal data: Use PII redaction in your transcription output or audio file to help protect customer privacy.
-
Improve staff training: Use criteria (sentiment, non-talk time, interruptions, talk speed) to flag transcripts that can be used as examples of positive or negative customer interactions.
-
Measure staff efficacy in creating a positive customer experience: Use sentiment analysis to measure if your agents are able to turn a negative customer sentiment into a positive one as calls progress.
-
Improve data organization: Label and sort calls based on custom categories (including keywords and phrases, sentiment, talk time, and interruptions).
-
Summarize the important aspects of a call using Generative AI: Use generative call summarization to get a concise summary of the transcript, which includes key components such as issues, action items and outcomes discussed in the call.
Real-time transcriptions:
-
Mitigate escalations in real time: Set up real-time alerts for key phrases—such as a customer saying "speak to a manager"—to flag calls as they begin to escalate. You can create real-time alerts using real-time category matches.
-
Improve handling of customer data: Use PII identification or PII redaction in your transcription output to help protect customer privacy.
-
Identify custom keywords and phrases: Use custom categories to flag specific keywords in a call.
-
Automatically identify issues: Use automatic issue detection to get a succinct summary of all issues identified in a call.
-
Measure staff efficacy in creating a positive customer experience: Use sentiment analysis to measure if your agents are able to turn a negative customer sentiment into a positive one as calls progress.
-
Set up agent-assist: Use the insights of your choice to provide your agents with proactive assistance in resolving customer calls. See Live Call Analytics and agent assist for your contact center with Amazon language AI services
for more information.
To compare the features available with Call Analytics to those for Amazon Transcribe and Amazon Transcribe Medical, refer to the feature table.
To get started, see Starting a post-call analytics transcription and Starting a real-time Call Analytics transcription. Call Analytics output is similar to that of a standard transcription job, but contains additional analytics data. To view sample output, see Post-call analytics output and Real-time Call Analytics output.
Considerations and additional information
Before using Call Analytics, note that:
-
Call Analytics only supports two-channel audio, where an agent is present on one channel and a customer is present on a second channel.
-
Job queueing is always enabled for post-call analytics jobs, so you're limited to 100 concurrent Call Analytics jobs. If you want to request a quota increase, see AWS service quotas.
-
Input files for post-call analytics jobs cannot be greater than 500 MB and must be less than 4 hours. Note that the file size limit may be smaller for certain compressed, non-WAV audio file formats.
-
If using categories, you must create all desired categories before starting a Call Analytics transcription. Any new categories cannot be applied to existing transcriptions. To learn how to create a new category, see Creating categories for post-call transcriptions and Creating categories for real-time transcriptions.
-
Some Call Analytics quotas differ from Amazon Transcribe and Amazon Transcribe Medical; refer to the AWS General Reference for details.
Dive deeper with the AWS Machine Learning Blog
To learn more about Call Analytics options, see:
To view sample Call Analytics output and features, see our
GitHub
demo
Region availability and quotas
Call Analytics is supported in the following AWS Regions:
Region |
Transcription type |
|---|---|
ap-northeast-1 (Tokyo) |
post-call, real-time |
ap-northeast-2 (Seoul) |
post-call, real-time |
ap-south-1 (Mumbai) |
post-call |
ap-southeast-1 (Singapore) |
post-call |
ap-southeast-2 (Sydney) |
post-call, real-time |
ca-central-1 (Canada, Central) |
post-call, real-time |
eu-central-1 (Frankfurt) |
post-call, real-time |
eu-west-2 (London) |
post-call, real-time |
us-east-1 (N. Virginia) |
post-call, real-time |
us-west-2 (Oregon) |
post-call, real-time |
Note that Region support differs for Amazon Transcribe, Amazon Transcribe Medical, and Call Analytics.
To get the endpoints for each supported Region, see Service endpoints in the AWS General Reference.
For a list of quotas that pertain to your transcriptions, refer to the Service quotas in the AWS General Reference. Some quotas can be changed upon request. If the Adjustable column contains 'Yes', you can request an increase. To do so, select the provided link.
