Amazon Lex launches new multilingual speech recognition models
News
Amazon Lex has launched new multilingual streaming speech recognition models (ASR-2.0) with enhanced accuracy across multiple languages.
- Two specialized language groupings: European and Asia Pacific
- European model supports Portuguese, Catalan, French, Italian, German, and Spanish
- Asia Pacific model supports Chinese, Korean, and Japanese
- Better recognition of alphanumeric speech like account and serial numbers
- Improved accuracy for non-native speakers and regional accents
- Supports regional language variants (e.g., European and Canadian French)
Customers can leverage these improvements by rebuilding their existing Amazon Lex bots, with the new models now available in all Amazon Lex V2 regions.
The AWS News Feed is currently looking for gold sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.
Related articles
Jan 13
2026
2026
Amazon Lex launches improved speech recognition models for English
Sep 16
2025
2025
Amazon Lex provides generative AI based enhanced natural language understanding in eight new languages
Jun 4
2025
2025
Amazon Lex extends custom vocabulary feature to additional languages
Jan 12
2026
2026
Amazon Lex launches configurable voice activity detection sensitivity
The AWS News Feed is currently looking for silver sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.