To meet the needs of our users, we are constantly evolving our DeepVA product. The latest version is packed with new features and enhancements that give you greater customizability and improved performance. Read now about our updates that make DeepVA even more powerful and user-friendly.
Applying Face Recognition in Live Streams
Gradually expanding our existing features for optimal use of DeepVA, what has been possible for Lower Third Recognition, Speech Recognition, and Landmark Recognition functions for some time now also applies to Face Recognition function: From now on, you can use facial recognition in live streams.
In the near future, we plan to offer this for other features such as Visual Concepts Recognition.
Translating Speech Recognition Transcripts into 27 Languages
Starting now, DeepVA users have the option to translate their extracted text from the Speech Recognition function into a total of 27 languages. This allows them to act quickly and efficiently in an international context.
Currently, this extension is only available for API users. However, starting from August 22, you will also have the option to use the translation function in the user interface

Improved Usability When Dealing with Speech Recognition Transcripts
The user experience has been enhanced by smoother scrolling and the ability to select individual words in the transcripts during audio or video playback. This enables seamless tracking of spoken words in the text.

What else is new? Bug Fixes & Co.
- Optimization of the user interface by avoiding redundant parent labels for Object- and Scene Recognition
- Resolution of an issue where Face Recognition failed in certain edge cases.
Try the latest version of DeepVA and experience the power of AI-driven analytics with advanced customization and improved performance. Discover the limitless possibilities and get deeper insights with DeepVA’s cutting-edge features.
All DeepVA changelog updates are available here: https://docs.deepva.com/changelog/