Skip to main content
Speech to text can be used to create a verbatim transcript of the audio; however, punctuation is essential for coherent documentation. Two optional features are available for this need: Spoken and Automated Punctuation.

Feature availability:

/transcribe

/streams

/transcripts

The two parameters, spokenPunctuation and automatedPunctuation are mutually exclusive - when both are set to true, spokenPunctuation will override automatedPunctuation.

Punctuation configuration request parameters

Spoken Punctuation Support


Notice the tabs atop the table above to see spoken punctuation phrases supported per language.Some punctuation may be supported by more than one utterance. For example, either “open parentheses” and “open paren” can be spoken to return (. There are also some terms (e.g., “colon”) that will be disambiguated by the language model to determine if the symbol or the word should be inserted based on the context.Contact us if you have issues with spokenPunctuation recognition or would like to see other alternative phrases added.

Don’t Smart Quote Me On That

Some applications provide support for “smart punctuation”: Transformation of plain ASCII characters to look nicer and be more readable in modern text editors. Such smart transformations, however, can cause issues with speech-to-text integrations. See a detailed guide here to learn how to insert and handle these characters appropriately, and prevent unexpected whitespace from being added into your text.
There are some terms (e.g., “colon”) that will be disambiguated by the language model to determine if the symbol or the word should be inserted based on the context.Please contact us to report errors, or for more information on this feature.