beta Learn about how Corti speech to text supports formatting of dictation text output
Formatting feature is currently in beta testing. API details subject to change ahead of general release.
Speech to text can be used to create a verbatim transcript of the audio; however, some content is not documented in the same manner as it is verbalized. The formatting features provide control over how key information should for represented in the textual output.
Defining formatting in configuration is optional. When these preferences are not configured, the default values listed below will be applied automatically.
Full support for the functionality outlined below is available in English (en), German (de), and French (fr).
Limited support for the functionality outlined below is available in Danish (da) - you can set the formatting values as desired, but results may be inconsistent. Additional language model finetuning in progress to address this limitation.
There are some terms (e.g., homophones) that will be disambiguated by the language model to determine if the symbol or the word should be inserted based on the context. Improvements on this front expected to continue.
