Skip to main content
Corti speech to text and text generation are specifically designed for industry use. Speech to text (STT) language models are designed to balance recognition speed, performance, and accuracy. Text generation LLMs accept various inputs depending on the workflow (e.g., transcripts or facts) and have defined guardrails to support quality assurance of facts and documents outputs.
The language codes listed below are used in API requests to define output language for speech to text and document generation.
  • Use the GET/languages/ request here to retrieve a list of available languages per endpoint.
  • Learn more about speech to text endpoints here.
  • Learn how to query the API for document templates available by language here.

​
Speech to Text Performance Tiers

Corti speech to text uses a tier system to categorize functionality and performance that is available per language:

​
Available Languages

The table below summarizes languages supported by the Corti API for use with speech to text (Transcribe, Streams, and Transcripts) and text generation (Facts and Documents) endpoints:

Notes:1 Use the listed language codes for the following parameters:
  • primaryLanguage in /transcribe, /streams, and /transcripts requests
  • outputLanguage in /streams configuration mode.type: facts
  • outputLanguage in /documents requests
2 Configure primaryLanguage as no for Norwegian Bokmål speech to text output. Document generation outputLanguage can support both Norwegian Bokmål (no-NB) and Norwegian Nynorsk (no-NN).3 Configure primaryLanguage as gsw-CH for dialectical Swiss German workflows (e.g., conversational AI scribing), and de-CH for Swiss High German dictation. Swiss German /streams configuration: Use gsw-CH for transcription.primaryLanguage and de-CH for outputLanguage in mode.type: facts.
Template(s) or section(s) used in /documents requests must be available for the language code defined for outputLanguage. If one is not available out of the box, you can build and customize templates as needed to support your language requirements.

​
Language Translation

  • Translation (audio capture in one language with transcript output in a different language) is not officially supported in the Corti API at this time.
  • Some general support for translation of transcripts in English to facts in other languages (e.g. German, French, Danish, etc.) is available in streams or extract Facts requests.
  • Additional translation language-pair combinations are not quality assessed or performance benchmarked.

Please contact us if you are interested in a language that is not listed here, need help with tiers and endpoint definitions, or have questions about how to use language codes in API requests.