Custom dictionaries
Our Custom Dictionary functionality biases the speech recognition algorithms of Amazon Transcribe and Speechmatics towards a pre-defined set of terms. It's extremely useful when you know what kind of words or names are going to appear in a given video. It's particularly effective for product names, names of people, technical jargon, and so on.
To use Custom Dictionary functionality, you need to create a new Custom Dictionary first:
- Navigate to the Custom Dictionaries page, available from the top-right dropdown
- Select your desired language, and then type (or copy & paste) in your required terms. There is a limit of 1000 words.
- Once you've finished, click Create
To manually populate phrases, insert the phrase as you would like it to appear in your captions into the ‘Phrase’ field. The ‘Sounds like’ field is optional and can be used for instances where the word itself doesn't give enough pronunciation detail, for example, Porsche 911, .NET, or a person or product name that may be phonetically unclear or ambiguous. CaptionHub will do its best to prompt you where pronunciation is unclear, but you may wish to look at some Custom Dictionary examples.
Having created your custom dictionary, you then need to specify it when you create a transcription:
- Click on the Create captions button, and choose Auto-Transcribe.
- As long as the transcription engine supports it, then the Custom Dictionary option will appear, with a drop-down
- Select the Custom Dictionary you'd like to use, and specify everything else as you would usually
Note
- Either Speechmatics, or Amazon Transcribe need to be selected in the Transcription section in Team Settings.
- Custom dictionaries are now available across all regional variants of a given language. For example, a dictionary created for English (UK) will also be accessible when transcribing into English (US), English (Global), and other variants—provided the ISO language code is the same. This update eliminates the need to create separate dictionaries for each regional variant and helps maintain consistency across dialects.
This applies when applying a dictionary to ASR (Automatics Speech Recogniation), whether you're auto-transcribing from the Original Captions tab in the UI or configuring original captions in your automation templates under the Original tab.
- Teams can set a default custom dictionary to be automatically applied to all original captions. To do this, go to Team Settings > Custom Dictionaries, click the three-dot menu next to the dictionary you'd like to use, and select Mark as default.