> ## Documentation Index
> Fetch the complete documentation index at: https://docs.corti.ai/llms.txt
> Use this file to discover all available pages before exploring further.
# Languages
> Learn about how languages are supported in Corti APIs
export const LanguageSearch = () => {
const ref = React.useRef(null);
React.useEffect(() => {
if (!ref.current) return;
const table = ref.current.parentElement.querySelector('table');
if (!table) return;
const rows = Array.from(table.querySelectorAll('tbody tr'));
const input = ref.current.querySelector('input');
const select = ref.current.querySelector('select');
if (!input || !select) return;
const apply = () => {
const q = (input.value || '').toLowerCase().trim();
const tier = select.value;
rows.forEach(row => {
const cells = row.querySelectorAll('td');
const name = (cells[0]?.textContent || '').toLowerCase();
const code = (cells[1]?.textContent || '').toLowerCase();
const rowTier = (cells[2]?.textContent || '').trim();
const textMatch = !q || name.indexOf(q) !== -1 || code.indexOf(q) !== -1;
const tierMatch = !tier || rowTier === tier;
row.style.display = textMatch && tierMatch ? '' : 'none';
});
};
input.addEventListener('input', apply);
select.addEventListener('change', apply);
return () => {
input.removeEventListener('input', apply);
select.removeEventListener('change', apply);
};
}, []);
return
;
};
Corti speech to text and text generation are specifically designed for use in the healthcare domain. 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](/api-reference/languages/list-languages) to retrieve a list of available languages per endpoint.
* Learn more about speech to text endpoints [here](/stt/overview).
* Learn how to query the API for document templates available by language [here](/textgen/templates#retrieving-available-templates).
***
## Speech to Text Performance Tiers
Corti speech to text uses a tier system to categorize functionality and performance that is available per language:
| Tier | Description | Medical Terminology Validation |
| :----------- | :--------------------------------------------------------------------------------------------------------------- | :----------------------------------------------------------------------------------------------------------------------------------------------------------------------------: |
| **Base** | AI-powered speech recognition, ready to integrate with healthcare IT solutions | `Up to 1,000` |
| **Enhanced** | Base plus optimized medical vocabulary for a variety of specialties and improved support for real-time dictation | `1,000-99,999` |
| **Premier** | Enhanced plus speech to text models delivering the best performance in terms of accuracy, quality, and latency | `100,000+` |
***
## Language Availability per Endpoint
The table below summarizes languages supported by the Corti API and how they can be used with speech to text endpoints (`Transcribe`, `Streams`, and `Transcripts`) and text generation endpoints (`Documents`):
| Language | Code1 | Performance | [Transcribe](/api-reference/transcribe) | [Streams](/api-reference/streams) | [Transcripts](/api-reference/transcripts/create-transcript) | [Documents2](/api-reference/guided-documents/generate-a-structured-document) |
| :---------------------------------------------------- | :------------------------------------------------------------------------------------: | :--------------------------------------------------------------------------: | :----------------------------------------------------------------------------------: | :------------------------------------------------------------------------------------: | :--------------------------------------------------------------------------------------------------------------: | :---------------------------------------------------------------------------------------------------------------------------------: |
| Arabic | `ar` | Enhanced | | | | |
| Bulgarian | `bg` | Base | | | | |
| Cantonese | `yue` | Base | | | | |
| Croatian | `hr` | Base | | | | |
| Czech | `cs` | Base | | | | |
| Danish | `da` | Premier | | | | |
| Dutch | `nl` | Enhanced | | | | |
| English (US) | `en` or `en-US` | Premier | | | | |
| English (AU) | `en-AU` | Premier | | | | |
| English (UK) | `en-GB` | Premier | | | | |
| Estonian | `et` | Base | | | | |
| Finnish | `fi` | Enhanced | | | | |
| French | `fr` | Premier | | | | |
| German | `de` | Premier | | | | |
| Greek | `el` | Base | | | | |
| Hebrew | `he` | Base | | | | |
| Hindi | `hi` | Base | | | | |
| Hungarian | `hu` | Enhanced | | | | |
| Italian | `it` | Base | | | | |
| Japanese | `ja` | Base | | | | |
| Korean | `ko` | Base | | | | |
| Latvian | `lv` | Base | | | | |
| Lithuanian | `lt` | Base | | | | |
| Malay | `ms` | Base | | | | |
| Mandarin | `cmn` | Base | | | | |
| Maltese | `mt` | Base | | | | |
| Marathi | `mr` | Base | | | | |
| Norwegian | `no` | Enhanced | | | | |
| Polish | `pl` | Base | | | | |
| Portuguese | `pt` | Base | | | | |
| Romanian | `ro` | Base | | | | |
| Russian | `ru` | Base | | | | |
| Slovakian | `sk` | Base | | | | |
| Slovenian | `sl` | Base | | | | |
| Spanish | `es` | Enhanced | | | | |
| Swahili | `sw` | Base | | | | |
| Swedish | `sv` | Enhanced | | | | |
| Swiss French | `fr-CH` | Premier | | | | |
| Swiss German | `gsw-CH`3 | Enhanced | | 4 | | |
| Swiss High German | `de-CH`3 | Premier | | 4 | | |
| Tamil | `ta` | Base | | | | |
| Thai | `th` | Base | | | | |
| Turkish | `tr` | Base | | | | |
| Ukrainian | `uk` | Base | | | | |
| Urdu | `ur` | Base | | | | |
| Vietnamese | `vi` | Base | | | | |
**Notes:** 1 Use the listed language codes for the parameters `primaryLanguage` in `transcribe`, `streams`, and `transcripts` STT requests, `outputLanguage` parameter in `streams` "facts" configuration, and `outputLanguage` in "create documents" requests.
2 Template(s) or section(s) in the defined output must be available for successful document generation. Adding `documents` support for languages without a check-mark can be provided upon request, or you can [build it out yourself](/textgen/template-creation).
3 Configure `primaryLanguage` as `gsw-CH` for dialectical Swiss German workflows (e.g., conversational AI scribing), and `de-CH` for Swiss High German dictation.
4 For Swiss German `/streams` configuration: Use `gsw-CH` for "transcription" `primaryLanguage` and `de-CH` for "facts" `outputLanguage`.
***
## 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](/textgen/facts_realtime#using-the-api) or [extract Facts](/api-reference/facts/extract-facts) requests.
* Additional translation language-pair combinations are not quality assessed or performance benchmarked.
Please [contact us](mailto:help@corti.ai) 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.