Languages Available Overview

Our speech architecture is engineered to handle the complexities of natural language processing (NLP) at scale. We support a diverse array of global locales, providing deep-learning models specifically tuned for the unique acoustic profiles of individual dialects. This matrix outlines the cross-functional availability of our Transcription, ASR, Call Progress Analysis (CPA), and Text-To-Speech (TTS) services, allowing architects to design sophisticated, multi-language workflows within a unified containerized environment.

Legend:

  Inverse Text Normalization (ITN): Converts spoken numerals, dates and currencies into formatted digits.
  Capitalization & Punctuation: Automatically applies grammatical structure and casing to raw transcripts.
  Sensitive Data Redaction: Identifies and masks PII/PCI data (e.g., credit card numbers, SSNs).
  Full Support: Feature is optimized and production-ready for this specific locale.


  LanguageTranscription
ASR		Post-Processing

Grammar ASR

CPA

TTS

Basque
(Euskara)


  

Cantonese

 

 

 


Catalan


 
 

Danish

 

 

 

 

Dutch

 


 

 

 

English: All dialects including US, UK, Indian, Australian, and NZ

 

    

 

 

 

French: All dialects including European and Canadian

   

    

 

 

 

Gaelic


  
Galician




German

 

    

 

 

 

Icelandic




 


Irish


  

Italian

 


 

  

Japanese

 


 

 

 

Korean

 


 

 


Lithuanian


  

Mandarin

 


 

 

 

Norwegian

 
  

 

Polish




 

 

Portuguese: All dialects including European and Brazilian

 

    

 

 

 

Romanian




  

  

Russian

 

  

 

 

 

Spanish: All dialects including Castilian (European), Mexican, and Latin American

 

    

 

 

 

Swedish

 
 

 

 

Swiss German

 


 

 


Turkish


 
Valencian


 

 

Welsh




 

 

Welsh English




 

 

 

Was this article helpful?