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
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.
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.
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.
Shipping continuously
Follow each release as Mallo gets sharper.
We’ll keep logging multilingual dictation, model setup, licensing, and workflow improvements here.