The Vocabulary feature in Superwhisper provides two powerful tools to improve your dictation experience: vocabulary words for better AI transcription recognition, and replacements for consistent post-transcription corrections.
When you add words to the vocabulary section, you’re providing the AI transcription model with custom recognition hints during the transcription process. These words are sent alongside your audio to help the AI recognize and accurately transcribe:
Replacements operate at the post-transcription stage of processing. Once your voice input is transcribed into text, any replacements you’ve configured will be automatically applied. This step is performed programmatically and does not rely on AI interpretation, ensuring that replacements happen exactly as you define them.
Replacements match words regardless of capitalization. The matching system is case-insensitive, so “todo” will match “ToDo”, “TODO”, or “Todo”. The replaced output will appear in the exact case you have specified for the replacement.
Replacements are the recommended solution for correcting persistent errors or expanding frequently used phrases. Because this feature operates independently of AI, the results are consistent and immediate, regardless of how the transcription model performs.
If you notice that certain words are consistently mis-transcribed, you can add multiple replacements to address every variation and point them all to the correct result.