Skip to content Skip to main navigation Skip to footer

Orbis Roadmap

On this page you will find the current Phonexia Orbis roadmap which provides an overview of our current product plans. Please note that the development, release and timing of any features or functions mentioned bellow are subject to change without prior notice. Therefore, his roadmap has only an information character, it is not a binding obligation.

Q4 2021

The first production version of Phonexia Orbis – version 1.0 will be released in November 2021. The version will include:

  • Manual files upload. Manual import of audio files including metadata (JSON metadata file supported)
  • User and Case management. Build-in User and Case management allows administrator to easily set up a team and the work accordingly.
  • Automatic voice recognition.  Based on cutting-edge Phonexia’s voice biometrics, Orbis will answer the question: “Who is speaking on the recording?”.
  • The most important first. The Hit feature provides the ability to set your own rules for highlighting the most important recording for you.
  • Smart audio player. Audio player is crucial part of the Phonexia Orbis. Enjoy the ability to play just the voice parts of the audio, assign the right person by the one click and many more.

Early Access Program – available for early adopters till the end of the year 2021.

Q1 2022

  • Person Groups. The Persons can be grouped into logical groups within the Case.
  • Automatic file upload. The utility for automatic files upload to the system to be ready.
  • Entities synchronization. The Orbis data model will be enriched by the CustomID parameter for better synchronization with 3rd party apps.
  • API for notifications. The new API endpoint for retrieving important notifications from the system.
  • High loads. This feature allows you to process a large number of audio files per hour and record tens of thousands of recordings in a single case.
  • Speaker clustering. This feature allows users to search for the same speakers within a pile of unknown recordings.


There are some key features under consideration for the next periods:

  • Shared voiceprint database. Would you like to create central voiceprint database for your Organization or share selected entities across the cases? This feature will make it.
  • Automatic transcription (Speech-to-text). We understand, that the content of the audio is crucial for the investigation.
  • Diarization. Do you want to detect multi-speaker recordings? This feature can do this and splitting the audio into multiple tracks with single speaker only. 
  • Advanced forensic analyses. Present the results of your forensic voice analysis to a court in the most convenient way.
  • Automatic translation. If you don’t understand the foreign languages within you case, this feature is for you.