Top 3 Tips To Increase Sales Using Speech Analytics

Posted by Emily Blazensky on Jan 30, 2017 10:31:09 AM



Millions of conversations pour into call centers worldwide every day. These calls carry priceless information that should be used to learn about your customers, such as; What's their ideal price-point? Which products will close this deal? Who is the decision maker here? What competitors are we getting matched up against to?

Successful sales teams analyze their phone calls and turn them into actionable data so they can improve on scripts and tactics that aren't working, and hone in on ones that are. By digging into this data, managers and reps can understand things like: how much should you let a customer talk, when should you bring up pricing, and how you should interpret a prospect's answer to key questions.

If your sales reps know what works before they pick up the phone, they’ll be much better equipped to overcome objections, qualify prospective leads, diffuse churn-inducing issues, and, all in all, become considerably more effective on the job.




To help our friends in the sales world out, we wanted to share these tips from our good friends at Gong who did an analysis on 25,537 sales calls. So, who is Gong? Gong is a pioneer in the Business Conversation AI space and they analyze phone calls to help teams improve their sales tactics. They make it easy for sales reps to see and improve on listening, pitching, probing, positioning and closing challenges. (The full published report can be found here).

If you didn't get a chance to read their analysis, here’s a quick summary of what type of data they gathered and how:

  • 25,537 B2B sales calls from 17 customers were analyzed. These customers were mainly mid-market, high growth SaaS companies. All of these calls were account executive conference calls conducted on platforms like GoToMeeting, Zoom, Webex, etc., rather than SDR or prospecting calls
  • Each call recording was mapped to its corresponding CRM record. This allowed Gong to analyze calls against outcomes like win-rates, forecast accuracy, sales cycle length, and revenue produced
  • As the calls were recorded, they were also speaker-separated, cleaned, and transcribed from speech-to-text
  • Finally, conversation analytics capabilities were used to analyze the calls and transcripts, auto-categorizing events within each call such as key moments, topics discussed, and seller/buyer behaviors


1. Talk Less

Screen Shot 2017-01-26 at 3.57.35 PM.png

The average salesperson may talk as much as 75% or more of the total call time. We get it, you're excited and you want to get all of those juicy sound bites out while you can. However, it turns out that top closers spend the most time listening and the least time talking. As you can see in the chart on the right, Top closers spend 41% of the time talking - that's less than HALF of the time! 



The average salesperson does not understand the value or benefit of the customer they are trying to sell to. If you are pitching for 3/4 of the call and not making a deal, there was clearly some disconnect.



2. Pricing Is Key

Screen Shot 2017-01-26 at 4.00.53 PM.png

Pricing should come up 3-4 times during the call, preferably after value has been established. This seems like a pretty obvious tip as the topic of "price" and "cost" usually pushes a prospect to evaluate their decision. However, what's interesting is that if pricing is mentioned too little, it has a similar effect.

Screen Shot 2017-01-26 at 4.01.51 PM.png

When pricing is discussed too early, chances of winning the deal become slim. In the graph above, you can see that the top closers tend to mention pricing towards the end of the call, once the value and benefit has been proven, rather than skew the rest of their presentation by mentioning it too early.


3. The Power of "Probably"

It turns out, when a prospect uses the word “probably” to estimate project timing, the accuracy of forecasting the project timing soars to 73%. Getting a prospect to use this term is a great indicator that things are moving in the right direction. 

Phrases like these are great to hear on a sales call:

  • "We'll probably be ready to go live next month."
  • "I'll probably have a decision made by next week."
  • "I think we'll probably be moving forward with you guys."


These kind of speech analytics learnings can be garnered from any batch of recordings a business may have. Image what we might find if we dug into last month's customer service calls, or inbound leads from our latest advertisement campaign? Harnessing the actual voice of the customer is the most accurate way to learn what they like, want and need. 



Topics: speech analytics, sales optimization

Written by Emily Blazensky

As Director of Marketing for VoiceBase, an API-based and enterprise grade speech analytics platform, Emily has developed unique and successful marketing strategies to meet the needs of an emerging industry leader, with a rapidly growing customer base. Emily has a keen grasp of the strategies to elevate awareness of the multiple ways speech technology can be applied to improve business process automation.
Find me on:

What is Big Voice?

AI-powered speech analytics for the cloud

VoiceBase is defining the future of deep learning and communications by providing unparalleled access to spoken information for businesses to make better decisions. With flexible APIs developers and enterprises build scalable solutions with VoiceBase by embedding speech-to-text, speech analytics, and predictive analytics capabilities into any big voice application. 

Subscribe to Email Updates

Recent Posts