Feature availability:
/transcribe
/streams
/transcripts
Punctuation configuration request parameters
Spoken punctuation is intended for punctuation that the speaker explicitly wants inserted into the transcript. Hyphens within compound words are handled automatically by the speech recognition model and generally should not be dictated.
Spoken Punctuation Support
- English
- Danish
- Dutch
- French
- German
- Hungarian
- Norwegian
- Swedish
Utilize the tabs atop the table to see spoken punctuation phrases supported per language.Notes:
- 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. - “Dash” returns the em-dash character (
"—") and will include a space on either side, while “hyphen” returns the hyphen character ("-") without spaces between the words and symbol. Use the former for separating two thoughts and the latter for word concatenation. Replacements can be used to override this default behavior.
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.