Version 3.6 Release: Enhanced Streaming, Auto Model Selection, and More in Our Data Privacy Platform

3.6

Share This Post

Hello, dear community!

We are thrilled to announce Private AI’s final release of 2023 with Version 3.6. Let’s explore what’s new and enhanced in this version.

Improved Connectivity and Performance with WebSocket

Clients are now able to connect over WebSocket. WebSocket provides a full-duplex communication channel over a single TCP connection, improving large-volume data processing. This feature is now available in Beta. For more information, check out the WebSocket Guide.

Audio Processing with Voice Distortion

Audio redaction now includes the ability to perform Voice Distortion.  Voice distortion makes it harder to identify the speaker. Take a look at the Audio Processing Guide for more information.

New Platform Accuracy Defaults 

The platform now defaults to “high_automatic.” This enhancement implies that when users opt for the default settings, the platform will prioritize selecting higher-capability models. 

Compared with previous versions, users employing default settings may observe different outcomes than previous versions. 

Support for File Extension and MIME Type in Base64 Route

By supporting both file extensions and MIME types in base64-encoded data, the platform becomes more versatile and user-friendly for different data types.

Enhanced Private AI Documentation 

Dive into our updated and improved documentation to better understand and utilize Private AI’s capabilities.

Model Improvements: Precision and Coverage

– AI Model Improvements: Enhanced detection of “spelled-out” entities: The platform better recognizes entities spelled out letter by letter, a common occurrence in call transcripts (e.g., “g as in golf, an as in apple, r for red, y for yellow,” “G-A-R-Y”).

– Healthcare Data Enhancements: The platform has improved the detection of Personally Identifiable Information (PII) and Protected Health Information (PHI) in healthcare data, particularly in single-word responses in patient forms and DICOM attributes.

– Regional Data Recognition:  The platform now handles more regional and multi-language variations than ever. Examples include Irish eircode (postal code) detection in English text and enhanced PHI detection in Dutch, English, Italian, and Ukrainian.

Cheers,
The Private AI Product Team

  •  
  •  

Sign up for our Community API

The “get to know us” plan. Our full product, but limited to 75 API calls per day and hosted by us.

Get Started Today

Subscribe To Our Newsletter

Sign up for Private AI’s mailing list to stay up to date with more fresh content, upcoming events, company news, and more! 

More To Explore

Download the Free Report

Request an API Key

Fill out the form below and we’ll send you a free API key for 500 calls (approx. 50k words). No commitment, no credit card required!

Language Packs

Expand the categories below to see which languages are included within each language pack.
Note: English capabilities are automatically included within the Enterprise pricing tier. 

French
Spanish
Portuguese

Arabic
Hebrew
Persian (Farsi)
Swahili

French
German
Italian
Portuguese
Russian
Spanish
Ukrainian
Belarusian
Bulgarian
Catalan
Croatian
Czech
Danish
Dutch
Estonian
Finnish
Greek
Hungarian
Icelandic
Latvian
Lithuanian
Luxembourgish
Polish
Romanian
Slovak
Slovenian
Swedish
Turkish

Hindi
Korean
Tagalog
Bengali
Burmese
Indonesian
Khmer
Japanese
Malay
Moldovan
Norwegian (Bokmål)
Punjabi
Tamil
Thai
Vietnamese
Mandarin (simplified)

Arabic
Belarusian
Bengali
Bulgarian
Burmese
Catalan
Croatian
Czech
Danish
Dutch
Estonian
Finnish
French
German
Greek
Hebrew
Hindi
Hungarian
Icelandic
Indonesian
Italian
Japanese
Khmer
Korean
Latvian
Lithuanian
Luxembourgish
Malay
Mandarin (simplified)
Moldovan
Norwegian (Bokmål)
Persian (Farsi)
Polish
Portuguese
Punjabi
Romanian
Russian
Slovak
Slovenian
Spanish
Swahili
Swedish
Tagalog
Tamil
Thai
Turkish
Ukrainian
Vietnamese

Rappel

Testé sur un ensemble de données composé de données conversationnelles désordonnées contenant des informations de santé sensibles. Téléchargez notre livre blanc pour plus de détails, ainsi que nos performances en termes d’exactitude et de score F1, ou contactez-nous pour obtenir une copie du code d’évaluation.

99.5%+ Accuracy

Number quoted is the number of PII words missed as a fraction of total number of words. Computed on a 268 thousand word internal test dataset, comprising data from over 50 different sources, including web scrapes, emails and ASR transcripts.

Please contact us for a copy of the code used to compute these metrics, try it yourself here, or download our whitepaper.