How to make dictation spell your names and jargon correctly
How do I stop dictation from mangling names and product terms?
Register each one in your Personal Dictionary. WisprBee then corrects them by sound rather than by spelling, so a term is fixed even when the transcript came back as a different but similar-sounding word — which is why this works where find-and-replace doesn't. On Pro and Pro Plus the Adaptive Dictionary also adds terms itself each time you correct a word, so the list builds without maintenance. Basic holds 50 terms; Pro and Pro Plus are unlimited.
Step by step
- 01
List the words that actually break
Colleagues' names, your product and feature names, company names, acronyms, and any technical term specific to your field. These are the words a general-purpose speech model has no way to guess.
- 02
Register each one in your Personal Dictionary
Open Settings → Personal Dictionary and add each term with the spelling you want. Enter it the way it should appear, not the way it was mis-heard.
- 03
Dictate a sentence containing a few of them
Check the output. Phonetic matching should correct the term even if the underlying transcript came back with a different spelling.
- 04
Let corrections accumulate
On Pro and Pro Plus, each word you fix afterwards is learned automatically by the Adaptive Dictionary. On Basic, add stragglers by hand as you notice them.
Worth knowing
- If a whole dictation came out wrong before you'd taught it a term, you don't have to say it again — re-transcribe that item from your history and the new dictionary entry is applied.
- For a shared vocabulary across a team — one dictionary everyone inherits — that's Pro Plus.
Terms used here
- Personal dictionary — A personal dictionary is a user-supplied list of names, product terms, acronyms and unusual spellings that a speech system should get right. It exists because proper nouns and jargon are where general-purpose transcription is weakest — the model has no way to know how you spell a colleague's name.
- Phonetic matching — Phonetic matching compares words by how they sound rather than how they are spelled, so that similar-sounding strings can be treated as the same word. It is what makes correcting a mis-heard name possible at all: find-and-replace cannot fix “Geoffrey” from an entry for “Jeffrey”, because the string it would need to search for is the one it never saw.
- Adaptive dictionary — An adaptive dictionary is a personal dictionary that populates itself from the user's corrections, rather than requiring entries to be added by hand. Every time you fix a word, the fix is learned.
- Re-transcribe — To re-transcribe is to re-run the processing of a saved dictation without speaking it again, producing a new output from the stored original. It is only possible if the raw input was kept.