lmstudio-ai / lmstudio-ai/docs

Clarify how to start Bionic voice keyboard from any macOS app

Open
#243 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
MDX
Stars
172
Forks
128
Avg merge
8m
Merged PRs (30d)
1

Description

Hi LM Studio team,

The Bionic launch blog says:

Use Bionic's voice keyboard to dictate into any app with local transcription.
Start the voice keyboard from any app, and Bionic will begin transcribing where your cursor is.

Blog post: https://lmstudio.ai/blog/introducing-lm-studio-bionic
Docs page found: https://lmstudio.ai/docs/bionic/voice-input

However, the docs page only mentions Settings → Voice → Auto load voice model. It does not explain how to actually start the global voice keyboard from another macOS app, nor whether this requires a menu bar item, global shortcut, permissions, or a separate setting.

Could you clarify the intended flow for macOS? Specifically:

  1. How does a user launch the Bionic voice keyboard while focused in another app?
  2. Is there a default global keyboard shortcut or menu bar control?
  3. Which macOS permissions are required? Microphone, Accessibility, Input Monitoring, etc.?
  4. Is this feature available in the current public Bionic build, or is it staged/coming soon?

A small addition to the Voice Input docs would help a lot, since the blog describes a system-wide feature but the docs currently only cover loading the voice model.

Thanks!

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start with the Bionic Voice Input docs page and the linked launch blog to compare the documented flow with the promised system-wide behavior on macOS. Confirm the launch method, shortcut or menu bar control, required permissions, and current availability, then document the verified flow and update the Voice Input page.

Written by the indexing model from the issue text.

Assessment

Tech stack
macos
Domain
documentation
Issue type
Documentation
Difficulty
2/5
Estimated time
1-3 hours
Activity status
Quiet
Clarity
Mostly clear
Newbie friendliness
58/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.