What's new in Azure Language?

Stay informed about recent releases and enhancements designed to help you get the most out of Azure Language capabilities. Azure Language is updated on an ongoing basis. Bookmark this page and stay up to date with release notes, feature enhancements, and our newest documentation.

Note

The release date and content listed below only correspond to actual deployment of the Azure Public Cloud in most cases.

This article provide the evolution history of Azure Language service on Azure Public Cloud for your reference that may not be consistent with the actual deployment on Azure operated by 21Vianet.

December 2025

Text PII detection enhancements (2025-11-15-preview API). The preview API introduces several new feature parameters for PII detection:

  • Anonymization. The syntheticReplacement redaction policy enables masking detected PII entities with synthetic replacement values. For example, "John Doe received a call from 424-878-9193" can be transformed into "Sam Johnson received a call from 401-255-6901."
  • Disable type-validation enforcement. Disable entity type validation to bypass strict validation when operational efficiency is prioritized over data integrity checks.
  • Confidence threshold score. Set a minimum confidence score threshold to control which entities appear in the output based on detection confidence.

Entity Tags generally available. Entity Tags are now generally available, providing enhanced metadata and categorization for named entities.

New preview model for PII detection. The updated preview model introduces support for the following new entity types:

Model improvements. Significant quality improvements for the following entity types:

October 2025

  • Summarization model 2025-06-10 generally available. The Summarization model version 2025-06-10 is now generally available. This model is fine-tuned using the Phi open model family, delivering enhanced performance for Issue and Resolution summary generation.

New Python SDKs. The new Python SDKs azure-ai-textanalytics 6.0.0b1 and azure-ai-textanalytics-authoring 1.0.0b1 are now available:

  • azure-ai-textanalytics 6.0.0b1 offers runtime APIs that enable users to utilize various prebuilt features within Azure Language, such as sentiment analysis, named entity recognition (NER), language detection, key phrase extraction, text PII detection, Text Analytics for health, and document summarization.

    Additionally, the SDK can be used to access inference APIs for custom NER and text classification models. This release supports the latest 2025-05-15-preview API, and previous versions. The 2025-05-15-preview API introduces several new capabilities:

    • Added support for new entity types in Named Entity Recognition (NER) and Text PII detection: DateOfBirth, BankAccountNumber, PassportNumber, and DriversLicenseNumber.

    • Enhanced functionality allows users to define values to be excluded from the results produced by Text PII detection.

August 2025

Release of new Text PII and NER model (2025-08-01-preview). This new preview model version introduces broader functionality and expanded capabilities for Text personal information identification (PII) and named entity recognition (NER) services:

  • Expanded language support for DateOfBirth entity. The DateOfBirth entity, which initially supported English only, now includes Tier 1 language coverage. This expansion supports French, German, Italian, Spanish, Portuguese, Brazilian Portuguese, and Dutch, ensuring broader international applicability.

  • Two new entity types added:

    • SortCode: A financial identifier used in the UK and Ireland to specify the bank and branch associated with an account.
    • LicensePlateNumber: Support is now available for standard alphanumeric vehicle identification codes. At this time, license plates that consist exclusively of letters aren't supported.

  • Improved AI accuracy in financial entity recognition. The 2025-08-01-preview model is further optimized to minimize both false positives and false negatives in financial entity recognition, resulting in greater accuracy and reliability.

New Python SDK release: azure-ai-language-conversations 2.0.0b1. The latest Python SDK, azure-ai-language-conversations 2.0.0b1, is now available and supports the 2025-15-05-preview REST API for conversation runtime.

  • Conversational Language Understanding (CLU) inference now allows for seamless integration with advanced large-scale language models, providing real-time recognition of user intent without the need for extra model training.
  • Enhanced intent prediction capabilities enable support for complex, multi-turn conversations. These advancements contribute to greater sophistication in conversational AI systems and, as a result, workflow automation processes are improved.

July 2025

Expanded .NET SDK support for text and conversation authoring APIs.

June 2025

New version of the Conversational Language Understanding (CLU) training configuration. This new version is aimed at minimizing over-predictions of the None intent—particularly in multilingual contexts—is now available via the REST API using trainingConfigVersion 2025-07-01-preview. For more information, see Train your model: request body data.

Updated Build your conversational agent accelerator project. The update includes a new routing strategy—TRIAGE_AGENT. This strategy uses an agent hosted on Foundry Agent Service. It utilizes Conversational Language Understanding (CLU) and Custom Question Answering (CQA) as tools to triage user intent for downstream agent routing. Additionally, these tools help deliver precise answers to specific questions. For more information, see TechCommunity Blog Post

.NET SDKs support. The following .NET SDKs are now available, and support the latest REST API version 2025-15-05-preview:

  • Azure.AI.Language.Text 1.0.0-beta.3 provides inference capabilities for a wide range of language processing tasks. These tasks include language detection, sentiment analysis, key phrase extraction, and named entity recognition (NER). The capabilities also include recognizing and linking personally identifiable information (PII) entities. Additionally, they offer text analytics for healthcare, custom named entity recognition (NER), and custom text classification. Both extractive and abstractive text summarization are also supported.

  • Azure.AI.Language.Conversation 2.0.0-beta.3 provides inference capabilities for conversational PII, conversational language understanding (CLU), and conversation summarization.

Text PII GPU container is now available for integration. You can access this container on the Microsoft Artifact Registry using the tag gpu.

May 2025

2025-05-15-preview release. The latest API preview version includes updates for named entity recognition (NER) and PII detection:

  • New entity type support for DateOfBirth, BankAccountNumber, PassportNumber, and DriversLicenseNumber.
  • Improved AI quality for PhoneNumber entity type.

PII detection enhancements. Azure Language introduces new customization and entity subtype features for PII detection:

March 2025

  • Back-end infrastructure for the Named entity recognition (NER) and Text Personally identifiable information (PII) entity recognition models is now updated with extended context window limits.

  • Our Conversational PII redaction service is now powered by an upgraded GA model. This revised version enhances the quality and accuracy of Credit Card Number entities and Numeric Identification entities. These entities include Social Security numbers, Driver's license numbers, Policy numbers, Medicare Beneficiary Identifiers, and Financial account numbers.

February 2025

  • Document and text abstractive summarization is now powered by fine-tuned Phi-3.5-mini! Check out the Announcing Blog for more information.

January 2025

  • .NET SDK for Azure Language text analytics, Azure.AI.Language.Text 1.0.0-beta.2, is now available. This client library supports the latest REST API version, 2024-11-01, and 2024-11-15-preview, for the following features:
    • Language detection
    • Sentiment analysis
    • Key phrase extraction
    • Named entity recognition (NER)
    • Personally identifiable information (PII) entity recognition
    • Entity linking
    • Text analytics for health
    • Custom named entity recognition (Custom NER)
    • Custom text classification
    • Extractive text summarization
    • Abstractive text summarization
  • Custom sentiment analysis (preview), custom text analytics for health (preview) and custom summarization (preview) were retired on January 10, 2025, as Azure AI features are constantly evaluated based on customer demand and feedback. Based on the customers' feedback of these preview features, Microsoft is retiring this feature and prioritize new custom model features using the power of generative AI to better serve customers' needs.

November 2024

  • Runtime Container for Conversational Language Understanding (CLU) is available for on-premises connections.
  • Both our Text PII redaction service and our Conversational PII service preview API (version 2024-11-15-preview) now support the option to mask detected sensitive entities with a label beyond just redaction characters. Customers can specify if personal data content such as names and phone numbers, that is, "John Doe received a call from 424-878-9192" are masked with a redaction character, that is, "******** received a call from ************" or masked with an entity label, that is, "PERSON_1 received a call from PHONENUMBER_1." More on how to specify the redaction policy style for your outputs can be found in our how-to guides.
  • Native document support gating is removed with the latest API version, 2024-11-15-preview, allowing customers to access native document support for PII redaction and summarization. Key updates in this version include:
    • Increased Maximum File Size Limits (from 1 MB to 10 MB).
    • Enhanced PII Redaction Customization: Customers can now specify whether they want only the redacted document or both the redacted document and a JSON file containing the detected entities.
  • Language detection is a built-in feature designed to identify the language in which a document is written. It provides a language code that corresponds to a wide array of languages. This feature includes not only standard languages but also their variants, dialects, and certain regional or cultural languages. Today the general availability of script detection capability, and 16 more languages support, which adds up to 139 total supported languages is announced.
  • Named Entity Recognition service, Entity Resolution was upgraded to the Entity Metadata starting in API version 2023-04-15-preview. If you're calling the preview version of the API equal or newer than 2023-04-15-preview, check out the Entity Metadata article to use the resolution feature. The service now supports the ability to specify a list of entity tags to be included into the response or excluded from the response. If a piece of text is classified as more than one entity type, the overlapPolicy parameter allows customers to specify how the service handles the overlap. The inferenceOptions parameter enables users to modify the inference process, such as preventing detected entity values from being normalized and added to the metadata. Along with these optional input parameters, we support an updated output structure (with new fields tags, type, and metadata) to ensure enhanced user customization and deeper analysis Learn more on our documentation.
  • Text Analytics for Health (TA4H) is a specialized tool designed to extract and categorize key medical details from unstructured sources. These sources include doctor's notes, discharge summaries, clinical documentation, and electronic health records. Today, we released support for Fast Healthcare Interoperability Resources (FHIR) structuring and temporal assertion detection in the Generally Available API.

October 2024

September 2024

August 2024

July 2024

  • Conversational PII redaction service in English-language contexts is now Generally Available (GA).
  • Conversation Summarization now supports 12 added languages in preview as listed here.
  • Summarization Meeting or Conversation Chapter titles features support reduced length to focus on the key topics.
  • Enable support for data augmentation for diacritics to generate variations of training data for diacritic variations used in some natural languages, which are especially useful for Germanic and Slavic languages.

February 2024

  • Expanded language detection support for added scripts according to the ISO 15924 standard is now available starting in API version 2023-11-15-preview.

January 2024

  • Last updated on