Start with a clear, small result.
This guide walks through one task: “Export a portable vocabulary backup.” The useful outcome is a complete, reviewable piece of text, rather than simply seeing an animation or a successful provider response. Use a synthetic example first, then repeat the task in the app and field where you actually work.
A personal dictionary has two distinct tools. Vocabulary hints influence recognition probabilistically. Exact replacements transform matched phrases after recognition. Use hints for unusual names and precise replacements for predictable phrases; do not treat a broad replacement as a general language correction.
One thought. Check the words.
Keep a copy of the words I use.
Keep a copy of the words I use.
Use the example as a test case, not a promise of identical automatic output. Speak in your own natural voice and note the exact words you said. If the result differs, separate a speech-recognition mistake from a change introduced by formatting or a destination-field problem.
A repeatable way through it.
- 01
Choose a short spoken phrase that the recognizer produces consistently. Test it in plain Dictation first.
- 02
Add the exact written result you want, including punctuation or a link when appropriate.
- 03
Check the replacement in a full sentence. Whole-word boundaries reduce accidental changes inside another word.
- 04
Prefer a specific phrase over a common single word. Longest matching phrases are applied first.
- 05
Keep an original transcript while evaluating a new rule. Remove a rule that changes unrelated meaning.
- 06
Export the dictionary before a large edit or import. Workspace and dictionary backups have different scopes.
Know which layer you are changing.
| Layer | What to check | What it proves |
|---|---|---|
| Device / edition | Desktop · Full Mac when using full Mac controls | You are testing the intended implementation |
| Microphone | Selected input, permission and Listening state | Capture is ready, not that the words are correct |
| Speech / text | Original transcript and optional formatting output | You can identify where meaning changed |
| Destination | Original field, cursor and complete result | The reviewed text reached the right place |
A successful microphone permission check does not establish recognition accuracy. A good original transcript does not establish that an AI rewrite preserved meaning. A finished result in Sayloom does not prove that another app accepted the paste. These distinctions make a failure more specific and easier to resolve.
A short review is worth the pause.
- ✓ The recording reaches Listening before the first word.
- ✓ The first and last intended words are present.
- ✓ Names, actions, dates and negation still mean what you intended.
- ✓ The destination or copy result contains the complete reviewed text.
A dictionary export is not a backup of API keys, model files or recordings.
If the task still fails, keep the expected sentence, actual result, edition and build number together. Change one setting per attempt. Use the free microphone diagnostic for signal checks; do not repeatedly spend trial uses trying to diagnose an unrelated formatting problem.
Keep the workflow honest.
Does this require an optional AI provider?
Plain Dictation does not require Ollama or a text-provider key. Email can use local layout. AI enhancement depends on the provider configured for that mode, and provider fees or privacy terms are separate. Check the original transcript before changing a writing provider.
Will this work the same way on every platform?
No. The full Mac Desktop, current Mac Store edition and mobile implementations have different capabilities. Mobile speech depends on device and language support. Review the relevant edition and use a supported editable field rather than assuming a Mac shortcut, model file or permission applies everywhere.
Product task guide · prepared from the Sayloom implementation and linked official references. Examples use synthetic text. Capabilities and prices can change; check the app and store before making a decision.