HoldToType

Compare

HoldToType next to the alternatives.

The programs people compare us with most often, in one table. Honest, including where we lose. Prices and features are what each maker publishes.

HoldToTypeHandyWispr FlowDragonWhisper FlowDictaFlowTypeless
Code-signed buildsNot yet iYesYesYesYesYesYes
PriceFreeFree$12 / month$699 onceFrom $9 / month$7 / month$12 / month
Subscription or creditsNoneNoneSubscriptionOne-time licenceCreditsSubscriptionSubscription
AccountNoneNoneRequiredRequiredRequiredRequiredRequired
Audio leaves your computerNoNoYesNoYesYesYes
Works offlineYesYesNoYesNoPaid optionNo
Open sourceMITMITNoNoNoNoNo
Languages9999100+7100+90+100+
Live text while speakingYesNoNoYesNoNoYes
Translation7 languagesNoNoNoNoNoYes
Editing by a local modelYesNoCloudNoCloudCloudCloud
Choice of speech model9 models, one per languageWhisper sizes and ParakeetNo, theirsNo, theirsNo, theirsNo, theirsNo, theirs
Your own speech modelsAny Whisper GGML file or sherpa-onnx model put in the models folderNoNoNoNoNo
Models that show text while you speakNemotron 3.5NoNoIts own engineNoNoIts own engine
Post-processing by a modelYesNoYesNoYesYesYes
Where post-processing runsOn your disk, or a server you chooseTheir cloudTheir cloudTheir cloudTheir cloud
Choice of editor modelAny GGUF from Hugging Face, or any APINoNoNoNoNoNo
Your own promptsYes, chains, each with a shortcutNoBuilt-in stylesNoBuilt-in edits
Recognition server on another computerYesNoNoNoNoNoNo
Voice commands you defineYesNoBuilt-in onlyYesBuilt-in only
Where dictation history is keptOn your disk, off by defaultOn your diskTheir serversTheir serversTheir serversTheir servers, on-device option
Interface languages8EnglishSeveral
Custom vocabularyYesNoYesYesYesYesYes
Portable folderYesNoNoNoNoNoNo

Prices and features as published by each maker in September 2026. A dash means the maker does not say.

Where we lose

No Mac and no phone. The builds are not code-signed yet, so Windows warns once. There is no cloud sync between your computers: settings and history live in the folder, and you copy them yourself.

Where it is a draw

Accuracy on everyday speech is close across the board: the same open models sit under most of these programs. Custom vocabulary is common. The paid ones ship a polished onboarding that a one-person project cannot match.

Where we win

Nothing to pay and nothing to sign up for. The audio never leaves the computer. The source is open under MIT. A model per language, live text while you speak, translation into seven languages, an editor model that runs on your disk, and a portable folder you can carry on a stick.

Not in the table

Windows voice typing, the built-in Win+H tool, is free and needs no install, but for most languages it sends the audio to Microsoft and it has no dictionary of your own words. Mac-only programs such as VoiceInk, FluidVoice or HoldType, the one with the similar name, are left out because HoldToType is for Windows. Vibe and other file transcribers do a different job: they transcribe recordings, not what you say at the cursor.

Download HoldToType