Fullscreen dictation now feels steadier and more responsive
The dictation HUD appears more reliably over fullscreen apps, reacts more smoothly when you start speaking, and behaves better when you toggle it quickly.
This update makes dictation feel calmer in the moment you actually use it. The HUD shows up more reliably over fullscreen apps, feels more polished when it appears, and holds up better when you trigger dictation repeatedly.
Better Over Fullscreen Apps
The dictation HUD now behaves more naturally over fullscreen apps, so it is easier to keep speaking without feeling like the overlay is fighting your workspace.
That matters most when Mallo is meant to stay out of the way. If the HUD feels dependable in fullscreen, dictation feels more like part of the flow and less like a special mode.
Faster, Smoother First Feedback
The HUD now gives feedback sooner when you press the hotkey, and the first appearance feels smoother instead of abrupt.
This makes Mallo feel more connected to your input. When the app responds right away, you spend less time wondering whether dictation actually started.
More Stable When You Toggle Quickly
Starting and stopping dictation rapidly now behaves more reliably, including the kind of repeated hotkey use that tends to show up in real work.
This is a small change on paper, but an important one in practice. Mallo should stay steady even when you use it quickly and without thinking about it.
Related updates
Keep reading
Qwen starts faster and fullscreen dictation feels smoother
Mallo now gets Qwen ready much faster on cold start, improves the default model path in onboarding, and behaves better over fullscreen apps.
Modifier-only hotkeys for dictation
Use a single modifier key like Command, Control, Shift, or Option for hold-to-talk or toggle dictation in Mallo.
Qwen and hotkeys are more ready when you are
We improved Qwen capture readiness and tightened hotkey behavior so dictation starts more reliably in the moments you actually reach for it.
Shipping continuously
Follow each release as Mallo gets sharper.
We’ll keep logging multilingual dictation, model setup, licensing, and workflow improvements here.