Amazon Transcribe Call Analytics provides more intelligence for customer service calls
Amazon Web Services Inc. is boosting its AWS Contact Center Intelligence offering with a new call transcription analytics tool that it said can generate more insights from customer conversations.
Announced today, Amazon Transcribe Call Analytics is a machine learning-powered conversation insights application programming interface. It’s meant to work with the existing Amazon Transcribe tool that’s used to generate transcriptions of customer service calls.
Amazon’s artificial intelligence and machine learning evangelist Julien Simon wrote in a blog post that even the most innocuous call with a potential or existing customer presents an opportunity to learn something about their needs an expectations. Those opportunities should not go to waste.
“For example, it’s important for customer service teams to figure out the main reasons why customers are calling them, and measure customer satisfaction during these calls,” Simon said. “Likewise, salespeople try to gauge customer interest, and their reaction to a particular sales pitch.”
Amazon Transcribe Call Analytics can be added to any contact center offering, not just AWS Contact Center Intelligence, Simon said, and used to analyze regular phone calls, web-based audio and video calls. Previously, customers would have to stitch AI services and ML models together by themselves to achieve this.
Amazon Transcribe Call Analytics is powered by natural language processing models trained on customer calls, and makes it easy to generate both an accurate transcript and actionable insights for each call.
“With a simple API call, developers can now easily add call analytics to any application, and extract customer insights from conversations without having to build AI pipelines and train custom ML models,” Simon continued.
Those insights will enable companies to better understand their customer service agents’ interactions with callers, identify trending issues and track performance metrics. Through this, businesses will gain intelligence on customer and agent sentiment, call drivers and even details relating to interruptions during the call, loudness, non-talk time and talk speed. Further, conversations can also be tagged based on keywords and phrases such as names, addresses, credit card numbers and social security numbers. Then, this information can be redacted from the transcribed text if desired.
“Making speech actionable remains a challenge for enterprises, but it is one of the big prizes for next generation applications,” said analyst Holger Mueller of Constellation Research Inc. “Amazon is trying to tackle user experiences because language is the most natural and therefore fastest way to interact with applications, hence why people say ‘voice is the new UI’. Amazon’s call transcription insights are a key step towards completing the puzzle.”
Amazon Transcribe Call Analytics is available in 21 languages and pricing is simplified, based on the number of call minutes only. It’s available in Amazon’s US West (Oregon), US East (N. Virginia), Canada (Central), Europe (London), Europe (Frankfurt), Asia Pacific (Mumbai), Asia Pacific (Singapore), Asia Pacific (Seoul), Asia Pacific (Tokyo) and Asia Pacific (Sydney) regions from today.
A message from John Furrier, co-founder of SiliconANGLE:
Show your support for our mission by joining our Cube Club and Cube Event Community of experts. Join the community that includes Amazon Web Services and Amazon.com CEO Andy Jassy, Dell Technologies founder and CEO Michael Dell, Intel CEO Pat Gelsinger and many more luminaries and experts.
We are holding our third cloud startup showcase on Sept. 22. Click here to join the free and open Startup Showcase event.
We really want to hear from you, and we’re looking forward to seeing you at the event and in theCUBE Club.