Skip to content
  • There are no suggestions because the search field is empty.

Dictionaries for Captions

Enhance the precision of your captions by incorporating dictionaries that account for local dialects, correct spellings of names, and commonly misidentified words.

Captioning customers can enhance the already remarkable accuracy of over 97% in their captioning by developing and managing a personalized dictionary within the CASTUS Cloud Portal. This dictionary allows you to provide a phonetic breakdown and display text for challenging names, terms, locations, and acronyms.

  1. Sign in to cloud.castus.tv/admin and choose Captions from the main menu followed by Caption Dictionaries.
  2. Create a new dictionary to get started, and add the phrase, sounds like, and display as fields for each item. 
  3. Hover over the question mark for each to display the rules for each field, or see below:
    1. PHRASE: Required. Every row in your table must contain an entry in this column. Do not use spaces is this column. If your entry contains multiple words, separate each word with a hyphen (-). For example, Andorra-la-Vella or Los-Angeles. For acronyms, any pronounce letters must be separated by a period. If your acronym is plural, you must use a hyphen between the acronym and the 's'. For example, 'CLI' is C.L.I. and 'ABCs' is A.B.C.-s. If your phrase consists of both a word and an acronym, these two components must be separated by a hyphen. For example, 'DynamoDB' is Dynamo-D.B..
    2. SOUNDS LIKE: Optional. Rows in this column can be left empty. Do not use spaces in this column. Include your entry as a hyphen-separated syllables that mimic how the word sounds. It's better to use small, common words over phonetic representations. For example, for 'Los Angeles', 'loss-an-gel-es' is preferred to 'lahs-ahn-jul-ees'.
    3. DISPLAY AS: Optional. Rows in this column can be left empty. You can use spaces in this column. Defines how you want your entry to look in your transcription output. For example, Andorra-la-Vella in the phrase column is Andorra la Vella in the Display As column. If a row in this colmn is empty, Amazon Transcribe uses the contents of the Phrase column to determine output.
  4. Save your changes.
  5. You can only use one dictionary at a time, so consider either consolidating your entries into a single comprehensive dictionary or logging into the portal in advance to select the dictionary you wish to utilize for your captioning.