Introducing MultiTrack Recording

When Two Is Not Enough: MultiTrack Recording Enables Recording Up to 32 Parties

Published September 10, 2018 by Kyle Riordan

To better facilitate conversations with customers and help businesses derive more value from them, Nexmo released our Split Recording offering. With it you can not only record calls but also split the audio recordings between the two parties, recording what someone hears and separately what he or she said.

This tremendously powerful tool allows you to do more with your recordings. For instance if you want to transcribe them, a singular recording composed of two people talking isn’t good enough. To a transcription service (machine, not person) it all sounds the same, and it would be impossible to identify which party said what during the course of the conversation. Any crosstalk could sound like a garbled mess, and even if both parties manage to avoid speaking over one another, without identifying who’s speaking the resulting transcription could resemble a Shakespearean soliloquy, minus terms like “thou” and “dost” (for most).

Knowing who said what makes the recording truly actionable, and allows you to dig into the transcription for keywords, new trends, and great business insights.

This scenario plays out across any of the other use cases you would want to apply to your recordings, like sentiment analysis. The clarity that split recording enables effects better outcomes and allows you to do more.

Introducing MultiTrack Recording

In that vein of enabling you to have more effective conversations with your customers Nexmo is excited to announce its newest Voice API release: MultiTrack Recording (patent pending). Just like Split Recording this feature opens up exciting possibilities for your audio recordings. The difference now is that you no longer are limited to just two participants. With MultiTrack Recording you can record up to 32 separate parties during a call.

This can be a tremendously powerful tool when added to a conference call. Think for instance how difficult it is to retain the contents of a meeting. Usually what ends up happening is one of two things.

  1. A participant volunteers to take notes and send them along to all the other participants. Usually the volunteer has their own contributions to make as well so getting every detail across every aspect of the meeting can be a real challenge.
  2. Everybody takes their own notes, jotting down what they individually deem important. Oftentimes there is no consolidation and the end result is little more than disparate musings that lack any real shared value.

Multitrack makes these flawed options a thing of the past. Just like with Split Recording you can now record each one of the participants individually so you have the full extent of who said what and when.

You can even take this innovation a step further by serving these recordings to a transcription service to make the insights truly actionable. With the audio transcribed to text you can do simple lookups to refresh your memory on dates, figures, specific topics—a photographic memory (or at least the benefits of one) is now just one “ctrl+f” command away.

And that is only one of the enhancements you can enable with MultiTrack recording. You can use it for your own records maintenance, forward the transcripts to sentiment analysis and other AI engines, and more.

Learning More

To learn more about our Multitrack update, Split Recording, or any of Voice features that can help you deliver a superior customer experience reach out to us.

Leave a Reply

Your email address will not be published.