Dictation still lands even when focus gets messy
Mallo now handles no-focus dictation more gracefully, so your words are less likely to disappear when there is nowhere obvious to type.
Dictation feels worst when it works technically but your words have nowhere to go. This update makes that edge case much less punishing.
Less Dead-End Dictation
Sometimes the active app does not expose a normal text field. Sometimes focus moves at the wrong time. Sometimes a target just refuses insertion.
Mallo now does a better job of keeping the result useful instead of letting the moment end in confusion.
A Better Fallback When There Is No Input
When there is no clear input target, Mallo can fall back more gracefully instead of making it feel like your transcript vanished.
That changes the feel of the app more than it sounds. A dictation tool needs to be trustworthy when the surrounding app state is messy, not only when everything is ideal.
Why This Matters
This is reliability work in the most practical sense. You finish speaking, and Mallo gives you a better chance of keeping what you said.
That is the difference between a dictation app that feels fragile and one you can use without second-guessing every context switch.
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.
Diagnostics and app plumbing got simpler
We simplified diagnostics helpers and core macOS app plumbing to make the app more stable and easier to evolve.
Shipping continuously
Follow each release as Mallo gets sharper.
We’ll keep logging multilingual dictation, model setup, licensing, and workflow improvements here.