01 / THE TASK

Start with a clear, small result.

This guide walks through one task: “Separate store access from provider charges.” 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.

Privacy depends on the path you choose, not the word AI. The included Mac speech runtime runs locally. Optional cloud speech sends audio to the provider you configure, and optional text formatting can send text or selected context. Inspect each path, permission and retention choice separately.

02 / A WORKED EXAMPLE

One thought. Check the words.

YOU SAY / SET UP
Check the store’s confirmed local price.
ILLUSTRATIVE EXPECTED RESULT
Check the store’s confirmed local price.

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.

03 / THE PLAYBOOK

A repeatable way through it.

  1. 01

    Identify whether the selected speech engine is local Whisper, on-device Apple Speech or an explicitly enabled cloud endpoint.

  2. 02

    Check which writing provider the current mode uses. Ollama on the Mac differs from an HTTPS text service.

  3. 03

    Review per-mode clipboard, selected-text, window and OCR settings. Enable only the context needed for the task.

  4. 04

    Decide whether audio should be retained for retry. Retention is off by default in the full Desktop app.

  5. 05

    Keep workspace and dictionary exports in a location you control. They may contain transcript text even though they exclude secrets and model files.

  6. 06

    Use real permission and storage boundaries. The offline trial is not a server-backed account system and cannot guarantee reinstall resistance.

04 / FOLLOW THE FLOW

Know which layer you are changing.

THE WORKFLOW, AT A GLANCEDestinationYour voiceReviewYour words
Speech recognition, formatting and insertion are separate stages. Check each stage before moving on.
Check the workflow before using a real message
LayerWhat to checkWhat it proves
Device / editionDesktop · Full Mac when using full Mac controlsYou are testing the intended implementation
MicrophoneSelected input, permission and Listening stateCapture is ready, not that the words are correct
Speech / textOriginal transcript and optional formatting outputYou can identify where meaning changed
DestinationOriginal field, cursor and complete resultThe 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.

05 / BEFORE YOU MOVE ON

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.
The detail that matters here

Lifetime access does not include hosted AI usage, and Apple and Google purchases are separate.

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.

06 / TWO USEFUL QUESTIONS

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.

REFERENCES

Go to the source.