FAQ
The questions that come up most.
Where do the models come from? Do I need the network?
Models download from a curated, measured list inside the app, file by file from the official repositories. If a direct connection fails, it falls back to a mirror automatically. After that, transcription is fully offline.
Does transcription upload my files?
In local-only mode, no. If you choose LAN compute, media is sent to your selected node, not to a cloud service.
Can several computers share the work?
Yes. Make another computer a node and jobs can run there. But nodes talk over plain HTTP, with no encryption and no tokens, so this belongs on trusted networks only.
Does anything keep running when I close the window?
Yes. A node is its own process and keeps working from the menu bar. Quitting the app asks first.
Which systems are supported?
macOS works. The build is ad-hoc signed and not notarized, so the first launch needs a right-click and Open. Windows installs, but the app is unsigned and will be blocked on machines with Smart App Control on.
Can I use the CLI or an AI client?
Yes. local-transcribe is the command-line client and voice-to-text-mcp is the local stdio MCP server. Both connect to the same local service, so they see jobs you started in the app.
What does uninstalling leave behind?
App data, models, job records and LAN media all stay in the app's Application Support directory. Uninstalling does not remove them; you delete them yourself.
Found a problem? How do I report it?
Opening a GitHub issue is the fastest way (github.com/TimmySheep/Local-Transcribe/issues) — include your macOS version and steps to reproduce. You can also email [email protected].
Does AI summarization need an internet connection?
Download a language model first. The desktop reader runs summarization and questions locally. Generated answers can be wrong, so check them against the transcript.