Formatting is currently in beta status. API details subject to change ahead of general release.
Speech recognition 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 configuration is optional. When these preferences are not configured, the default values listed below will be applied automatically.

Formatting options

Dates

OptionFormatExample
0As dictated”February third twenty twenty five”
1Long date (default)“3 February 2025”
2Short date (US)“02/03/2025”
3Short date (EU)“03/02/2025”
4ISO”20250302”

Times

OptionFormatExample
0As dictated”Four o’clock” or “four thirty five” or “sixteen hundred”
112-hour”4:00 PM”
224-hour (default)“16:00”

Numbers

OptionFormatExample
0As dictated”one, two, … nine, ten, eleven”
1Single digit as words, multi-digit as number (default)“One, two … nine, 10, 11”
2Numbers only”1, 2, … 9, 10, 11”

Units

OptionFormatExample
0As dictated”Millimeters, centimeters, inches”
1Abbreviated (default)“mm, cm, in”

Abbreviations

OptionFormatExample
0As dictated”Blood pressure one twenty over eighty”
1Abbreviated (default)“BP 120/80”

Ranges

OptionFormatExample
0As dictated”one to ten”
1As numbers (default)“1-10”

Ordinals

OptionFormatExample
0As dictated”First, second, third”
1Abbreviated (default)“1st, 2nd, 3rd”
Use of the formatting settings is optional for dictation configuration. If no configuration is present for a given formatting category, then the default as defined above will be applied.Please contact us for more information on format options, or for issues with formatted output.