We are off to a rocking great year fueled by you, our growing customer base, as well as the synergies from the broader Cisco ecosystem. On top of us lowering our domestic prices on the first day of 2016 we have more exciting news for you:
Tropo will be coming to Europe in spring 2016 as http://www.tropo.eu
Tropo.eu is our response to customer requests for tighter alignment to European privacy and data security laws. With this upcoming launch, we’ll be enabling a protected instance of Tropo in the UK serving all of our European customers.
We have leveraged our deep experience putting Tropo in private, highly secure data centers around the world and will release our European instance with your data privacy in mind. Your confidential data will remain within the borders of the EU and we will be able to provide you with the highest call quality and lowest latency for EU to EU calls out of our Tropo.eu portal.
Initially, when we launch this spring, we will have some additional processes in place: For example to get numbers in Germany you have to provide your proof of address.
We will provide more details over the next few months at http://www.tropo.eu. If you cannot find what you are looking for or need more information, please contact email@example.com.
We hope you are as excited as we are that we are finally able to deliver a product that will resonate with companies of all sizes in a very important market to us.
Come see us in action!
For those of you at Cisco Live! Berlin next week, we invite you to stop by the Tropo booth in the DevNet Zone to learn more about this announcement and receive a demo of our voice and SMS offerings. There will also be a series of Tropo API introductory sessions and learning labs available throughout the week. View the session times and locations here.
Be sure to follow us on Twitter @Tropo for the latest information, tips and events that we will be at!
It’s been a busy six months since Tropo joined Cisco and while we’ve been quiet for much of this time there has been a LOT going on. First and foremost, we should let you know that Cisco is committed to maintaining and growing Tropo. To that end we are announcing new lower pricing for US Domestic calls, messages and phone numbers. US Phone numbers now cost only $1 per month (2$ for toll free) and messages and calls start as low as 3/4 of a cent per message or per minute! As part of Cisco we can apply better economies of scale and we want to pass those savings on to our users. These changes went into effect starting today, January 1, 2016, and will automatically be applied to all customers except for those that have Enterprise contracts with us. Look for changes to our international pricing later in the year!
In addition to growing and expanding Tropo as it exists today, the Tropo team is also helping Cisco grow a more developer friendly culture. This is in Tropo’s DNA and the team at Cisco has asked us to take our experience creating APIs that developer’s love and apply it to the broader Cisco Collaboration offering. You can see the first examples of this at the new Developer portal for Spark. The great news for Tropo developers about this work is that we will be working to make these new collaboration APIs available to Tropo to developers so that they can embed additional real time communication capabilities like video and IP messaging in addition to the voice and SMS capabilities that we have today.
As a follow up post to the Tropo voicemail detection application demo, I wanted to expand on the topic of accuracy for voicemail detection on outbound calls. Since detection accuracy is a rather ambiguous term and one that’s open to a lot of interpretation, some additional insight is probably called for.
In truth, the only way to know if an answered call was detected accurately or not is to have a human score the call. In other words, someone has to actually make a determination if the call was human or machine and compare that against the automated detection. This can be accomplished in a couple different ways.
The best method that would yield the most honest results would be to record all outbound calls, or at least random sampling of calls. From there, log the detection result (HUMAN, MACHINE, etc.) in the application and in parallel, have a human note the actual result. Accuracy is then quantified by the percentage of calls that have the same result logged by the manual review and the automated detection.
The second approach to this is more commonly used to score voicemail detection accuracy. Outbound calls answered by humans often end up being routed to a human agent. So when an agent receives a transferred call that was actually answered by a machine, they score it accordingly. This means they’re only ever scoring calls that are detected as human. As such, when you hear other providers boast 90%+ detection accuracy rates, this is the method they’re most likely using. Using this statistic, out of every ten calls they think are human, nine really are. However, they will have no idea how many calls they classified as machine that were really answered by a human. So all this metric means is “when we think it was a human, we were right 90% of the time.” Using this same logic, one could claim 100% accuracy rate by simply classifying all calls as a machine and never picking human at all.
Additionally, testing voicemail detection strictly in a lab setting can also yield overly optimistic scores due to the limited amount of “real” calls that can actually be run. To get real-world results, score the calls during a live outbound campaign that reaches a variety of voicemail/answering machines and individuals who answer the phone in their own unique way.