User Guide

1. Start dictating

Select a supported text field, press ⌃⌥ (Control + Option), speak, then press the shortcut again. Saywave attempts to insert the result at the active cursor. Dictation inserts text directly without reading or replacing your clipboard. Secure fields and some custom app controls may reject automated insertion; the result remains in History so you can copy it yourself.

For push-to-talk, open the menu-bar icon and choose Switch to Push-to-Talk. Saywave then records while you hold ⌃⌥ and stops when you release it.

Updating an existing installation

Use Check for Updates in the Saywave menu. Version 1.6 upgrades legacy installations to a free lifetime licence for their current Mac without using another paid activation. Connect once after updating; after activation, the licence works offline. Settings → Licence lets you recover activation and copy a private backup code. If you start another recording before an earlier result finishes, the earlier text is kept in History and is not pasted into the newer recording. Storage failures appear in Settings; keep any unsaved text until the storage problem is resolved.

Read the dictation indicator

The floating indicator shows the input level, a live text preview, and status messages. Press Esc or click the indicator to cancel. You can drag it to another position, which Saywave remembers.

2. Choose a model and language

Open the menu bar's Model submenu to choose a supported speech engine. The available options include Whisper, NVIDIA Parakeet, and Apple's on-device engine on supported macOS versions. Parakeet v3 is the default. Accuracy and speed vary by language, hardware, audio quality, recording length, and model.

First use has two stages: downloading the model (about 470 MB for Parakeet v3), then preparing it once on your Mac, which usually takes under a minute. The setup window and the menu-bar panel show the download progress, the time left and the current stage. On macOS 26 and later you can dictate right away: Apple's on-device engine handles dictation until Parakeet is ready, then Saywave switches over by itself. On earlier macOS versions, start dictating when the panel says it is ready. Downloaded models stay loaded while resources allow, making later switches faster. A macOS update or cleared system cache may require preparation again.

Use the Language submenu to select your spoken language. Saywave selects a compatible multilingual engine for the language you choose.

3. Choose what happens to the transcript

The Mode submenu controls how Saywave handles the transcript:

• Raw: use the speech model's transcript without cleanup.
• Clean: remove filler words and adjust punctuation and capitalization.

Settings → Cleanup contains the same Raw and Clean choices. Review transcripts before relying on them; speech recognition can make mistakes.

Use spoken formatting commands

Say "new line", "new paragraph", or "bullet point" to insert formatting in supported languages. These commands work in Clean mode and can be disabled in Settings → Cleanup.

4. Use vocabulary and history

Add vocabulary

Settings → Dictionary corrects recurring spelling mistakes after recognition on every model. Enter the wording Saywave usually writes on the left and the spelling you want on the right. Both fields are needed for a replacement. Saved names with an empty left field are kept, but may not change the transcript.

Review local history and statistics

Settings → History stores dictations locally so you can copy them again. Statistics tracks words dictated, speaking time, and words per minute on the device.

5. Capture a meeting

Open the menu bar's Meeting submenu and choose Start Meeting Capture. Saywave records microphone and system audio, then creates a speaker-labelled transcript. Choose Stop Meeting Capture when the call ends.

The first capture requires macOS Screen Recording permission because that permission also covers system-audio capture. Saywave does not record or store video. Open Saywave Settings → Permissions to check microphone and Screen Recording access. Use the button beside a missing permission to open the relevant macOS page, then return to Saywave. Quit and reopen Saywave only if macOS asks.

Use automatic capture carefully

Auto-Capture in Zoom, Teams & FaceTime starts and stops capture with those apps. It is off by default. Enable it only when your workflow gives every participant advance notice and obtains any required consent before capture begins.

Read, search, and export

Captures appear in Settings → Meetings. Search by app, date, speaker, or transcript text. You can copy the full transcript, copy one voice, or export a Markdown or plain-text file. Click a speaker label to name that voice for the meeting.

Remember voices across meetings is off by default. When enabled, named voice fingerprints stay on the Mac and can be managed or forgotten in the Meetings pane.

Manage saved meetings

New meetings produce transcripts without generated summaries or action items. Older saved summaries remain available. Delete individual meetings from their row or use Clear All.

6. Fix common problems

Dictation does not insert text

Check the menu-bar status. If the microphone captured silence, confirm the input selected in macOS Sound settings or use Saywave's Input submenu. If transcription works but insertion fails, try a standard non-secure text field.

A permission is missing

Open Permissions… from Saywave’s menu, or Settings → Permissions. The checklist shows which permissions are granted and takes you to the correct macOS Settings page when access is missing. Microphone and Accessibility are required for dictation; Screen Recording is only needed for meetings. If insertion fails after a permission changes, your transcription remains in History so you can copy it.

A model is slow the first time

First use can include a download and an optimization step. Duration depends on the model, hardware, available memory, and network connection.