How can I correct a word that is often mistranscribed ?

You can customize how certain words, names, or phrases are spelled in the final transcript.

To use custom spelling, provide a dictionary through the custom_spelling_config parameter.

This dictionary should contain the correct spelling as the key and a list of one or more possible variations as the value.

Why use custom spelling?

Custom spelling is useful in scenarios where consistent spelling of specific words is crucial, such as:

Technical terms in industry-specific recordings
Brand names
Personal names with multiple possible pronunciations

<aside> 💡

The keys in the dictionary are case sensitive, while the values aren’t. Values can contain multiple words.

</aside>

Example Request Data


{
  "custom_spelling": true,
  "custom_spelling_config": {
    "spelling_dictionary": {
      "Gorish": ["ghorish", "gaurish", "gaureish"],
      "Data Science": ["data-science", "data science"],
      ".": ["period", "full stop"],
      "SQL": ["sequel"]
    }
  }
}

Custom Spelling Configuration Object

Key / Field	Type	Description	Example
`custom_spelling`	Boolean	Enables or disables custom spelling.	`true`
`custom_spelling_config`	Object	Contains configuration for custom spelling.	`{ "spelling_dictionary": { ... } }`
`spelling_dictionary`	Object	Dictionary where keys are the correct spelling, and values are lists of variations (case-insensitive).	`{ "Gorish": ["ghorish", "gaurish"] }`

How it works

The model will ensure that “Gorish” is spelled correctly throughout the transcript,
even if it is pronounced as “ghorish”, “gaurish”, or “gaureish”.
The same rule applies for “Data Science”, the punctuation ".", and “SQL”.