docs
Five cases cover almost everything. If yours is not here, the log usually names the cause, and an issue on GitHub gets an answer from the person who writes the program.
Another program holds the same shortcut. Change it in Controls & behaviour. If the program was started as administrator and the target window was not — or the other way round — Windows will not deliver the keys; run both at the same level.
Wrong device or a muted microphone. The Microphone section has a live meter and a record-and-play test.
Either no model is installed for that language, or the recognition server was pointed at another computer whose address is empty. The Status screen names which one and takes you there.
Since 0.75.4 the program checks the port before starting an engine and refuses if something else holds it. The message names the port; change it in System, or stop the other program. Two copies of HoldToType on one machine need different ports.
Tray menu → Open log. It is plain text, written in English whatever the interface language is, and it counts characters instead of quoting what you dictated. The last twenty lines usually name the cause.
2026-09-01 11:00:25 ready: hotkey=ctrl+win engine=sherpa model=models/nemotron-3.5 2026-09-01 11:02:41 dictation: 11.4 s captured, 0 network requests 2026-09-01 11:02:42 replacements: 62 -> 64 characters 2026-09-01 11:02:42 pasted 64 characters into code.exe
Completely, once a model is on disk. Recognition, translation by the model, prompts and every rule run on your own machine. The only things that need the network are downloading a model and checking for an update, and both happen when you ask.
No. Everything runs on the processor. A narrow model turns a normal sentence into text in well under a second on an ordinary laptop; the large Whisper models are slower and want more memory.
Whisper covers about a hundred. Beyond it the catalogue has models for particular languages and families: 25 European languages in one, about 30 in another, and single-language models that are faster and more accurate than anything general.
The program with its engines is about 100 MB. Models are what take room: from 150 MB for the smallest to about 1.5 GB for Whisper Medium. You download only the ones you use.
It might. The builds are not code-signed yet, so Windows warns about an unknown publisher. Every release publishes the SHA-256 of both files so you can check what you downloaded, and signing is on the roadmap along with the Microsoft Store.
Yes. The portable build writes nothing outside its own folder — settings, models and history all live there. Copy the folder to another machine and it carries on.
It is held in memory while you hold the keys and dropped as soon as it has become text. It is never written to disk as a file and never uploaded, unless you deliberately set up recognition on another computer.
Nothing. MIT licence, no account, no subscription, no paid tier waiting behind a feature.
Open an issue on GitHub or write to holdtotype@outlook.com. Say which version, which model and what the last twenty lines of the log say.