Skip to content
ImprovementMarch 21, 2026Mallo Team1 min read

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.

Speed is not only about cold start. It is also about whether dictation is ready at the exact moment you press the key and start speaking.

Qwen Feels More Ready In Use

This pass improves the way Mallo keeps Qwen prepared for dictation without making the whole app feel heavier.

The result is a dictation path that feels less hesitant when you jump in quickly, especially in the first second that matters most.

Hotkeys Behave More Predictably

We also tightened hold-to-talk behavior around the Fn + Space path so Mallo is less likely to miss the intent behind the shortcut.

That kind of fix sounds small, but it changes whether the app feels crisp or slightly out of step with your hands.

Why This Feels Better

Good dictation software should feel ready before you think about it. The app should meet you at the shortcut, not make you wonder whether it really caught the trigger.

This update moves Mallo closer to that feeling.

Related updates

Keep reading

FeatureMar 9, 20261 min read

Managed Qwen setup inside Mallo

Install Qwen3-ASR-1.7B-8bit from the Models page with a managed runtime path instead of a manual Python setup.

Read update
FeatureMar 12, 20261 min read

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.

Read update

Shipping continuously

Follow each release as Mallo gets sharper.

We’ll keep logging multilingual dictation, model setup, licensing, and workflow improvements here.