Speech recognition is trained on general language, so a colleague's surname, your product's name or a drug name is exactly what it gets wrong most often. Custom vocabulary for transcription is the fix: you add a word once to ThinkScribe's custom dictionary, and it helps every later transcription get it right. This guide explains why these words go wrong, shows the two ways they get into your dictionary, and sets out what a dictionary can and cannot do.
Why speech models get names and jargon wrong
A recognizer does not hear letters. It turns sound into the most probable sequence of words, and probable is decided by what it was trained on. Three things make a word improbable however clearly you say it.
It was never in the training vocabulary. Training data is dominated by ordinary language. A surname shared by a few thousand people, a compound place name, a molecule, an internal project code: none appear often enough to be learned, so the model reaches for the nearest thing it knows. That is why an unusual name comes back as two ordinary words that sound roughly the same.
Homophones. Many names are acoustically identical to everyday words: Reed and read, Wright and right, Cole and coal. Nothing in the sound separates them, so only context decides, and a model with no reason to expect a name picks the common word.
Rare words in ordinary sentences. Recognizers weigh each word against the words around it, so a long drug name between two plain English words competes with much likelier alternatives. The same goes for acronyms said as words and for a term from a second language dropped into your main one.
None of this is fixed by speaking more slowly. The word has to be made likely, which is what a dictionary does.
How to add a custom word to transcription
- On iPhone or iPad, open Settings with the gear in the Record or Library toolbar.
- Go to Advanced > Custom Dictionary. On Mac, open Settings (Command-comma) and choose Vocabulary.
- Add the word or phrase exactly as you want it spelled. Multi-word phrases are fine: a full name, a product line, a project code name.
- Record or import as usual. The next transcripts use your list.
Let your corrections teach it
You do not have to remember to add every word. When you correct the same word in your transcripts three or more times, ThinkScribe adds it to your dictionary for you. So the first week of fixing names by hand quietly builds the list you need.
What a custom vocabulary actually changes
In speech recognition generally, a custom vocabulary helps in two ways:
- Hints while recognizing: when the audio is ambiguous, the recognizer leans toward words on your list. A name it has never seen becomes a likely choice instead of an impossible one.
- Correcting afterwards: near-misses, such as a name split into two ordinary words or a product name with the wrong spelling, can be matched back to your entry.
Your custom dictionary is kept in ThinkScribe, and like your recordings and transcripts, it is never sent to us.
Hints versus corrections: why some words still slip
These are two different repairs, and they fail differently.
Biasing acts while the audio is decoded, so it can rescue a word that would otherwise never be produced at all. The audio still has to be close: a name pronounced nothing like its spelling stays out of reach however heavily it is weighted.
Correcting acts on the finished text, so it is predictable and works whatever produced the words, but it can only fix what still looks like a mistake. If a surname was heard as a different ordinary sentence, nothing is left to match against.
So prefer distinctive words. "Renner" is a safe entry. "Bill" is not, because half its occurrences are ordinary English and a replacement pass cannot tell which is which.
What is worth adding to a custom dictionary
Good candidates:
- People: colleagues, clients, patients, students, the guest you interview every week.
- Organizations and products, including your own.
- Domain terms the engine mangles: drug names, legal Latin, acronyms said as words, place names.
- Terms in a second language that come up inside your main language.
By field:
- Medicine: the drug names you dictate most often, procedure and device names, anatomical terms from your specialty, the named signs and scales, and the surnames of referring clinicians. Ward and clinic names count too, being local proper nouns no general model has seen.
- Law: case names you cite repeatedly, the Latin that survives in practice, statute short titles, and the names of counsel, judges and firms in your matters.
- Engineering and software: component, library and service names, the code names of projects and environments, and part families. Anything that looks like a normal word but is not, such as a service named after an animal, is worth adding, because the model will always prefer the animal.
Not worth adding:
- Ordinary words the engine already gets right.
- Spelling variants of the same word; add the one you want.
- Very short acronyms said letter by letter, which are usually recognized fine as letters.
- Words that came up once and you have already fixed by hand.
The cheapest way to build a list is to note the words you correct twice in your first week. Those, and only those, belong in it.
Use it with recordings, imports and voice typing
Your list is there for what you transcribe with ThinkScribe: recordings, imported files and dictation. On Mac, a name that keeps coming out wrong in Option-Space dictation is one Vocabulary entry away from fixed.
Names matter most when the transcript is going to be quoted. Interview transcription for journalists shows how a short list of names and places saves the most checking time, and the complete voice to text guide covers the rest of the workflow.
For medical and legal work
Drug names, procedure codes and case names are the words a general model stumbles on. With ThinkScribe they are transcribed on your device, and your recordings, transcripts and dictionary are never sent to us. Check your own professional and legal obligations before you rely on any tool for clinical or client material. Private dictation for medical and legal work goes into the workflow; this guide is the mechanics.
Frequently asked questions
Does adding a word guarantee it is recognized?
No. Biasing makes the word much more likely when the audio sounds close to it, and correction catches common near-misses, but a name pronounced very differently from how it is spelled can still be missed. Correcting it in a few transcripts adds it automatically, and those corrections are the fastest way to find out which spelling works.
How long should my list be?
Keep it short. Thirty names and terms you actually use work better than hundreds copied from a glossary, because a very long list dilutes the hints and can nudge unrelated words.
Where do I add words on iPhone and on Mac?
On iPhone and iPad, open Settings from the gear in the Record or Library toolbar, then Advanced > Custom Dictionary. On Mac, open Settings and choose Vocabulary. Words you correct three or more times in transcripts are added automatically.
Why does the same word come out right in one recording and wrong in the next?
Because biasing only tips a decision that was already close. Clear speech from a near microphone gives a strong signal and your word wins easily; a noisy room or a fast aside gives a weak one, and the ordinary word the model has heard a million times wins instead.
Is my custom dictionary sent anywhere?
It is never sent to us. There is no account, and transcription runs on your device. If you turn on iCloud Sync, your transcripts go to your own iCloud account, provided by Apple; your recordings and transcripts are still never sent to us.
