Help center
How can we help?
Guides for setting up wispa, picking a model, building modes and voice commands, and fixing the occasional snag.
Getting started
Install wispa, learn the dictation flow, and get your shortcuts down.
How wispa works
wispa is a push-to-talk voice keyboard for your Mac or Windows PC. Hold a key, speak, and your words are typed into whatever app you are using.
3 min readInstalling wispa
Download wispa for your platform, open it once, and grant two quick permissions so it can hear you and type for you.
3 min readKeyboard shortcuts
wispa is driven by a few global hotkeys. Here are the defaults and how holding differs from tapping.
2 min readTroubleshooting
The handful of things that trip people up, and how to fix each one in a minute.
3 min readModels and languages
Local and cloud transcription, which model to pick, and the languages wispa understands.
Transcription models
wispa can transcribe with local models that run on your device or cloud models that use your own API key. Here is the full lineup.
3 min readLocal vs cloud models
Local models run on your device and keep audio private; cloud models use your API key and are quick to set up. Here is the trade-off.
3 min readWhich model should I choose?
Pick a model by what matters most to you, privacy, speed, accuracy or a light footprint. Here is a cheat sheet.
3 min readDownloading and managing models
The model library is where you download local models, switch which one is active, and free up space when you no longer need one.
2 min readLanguages
wispa transcribes dozens of languages through Whisper, and its own interface comes in English, German, Spanish and French.
2 min readCloud keys and providers
Bring your own API keys for cloud transcription and AI cleanup, and see which provider does what.
Cloud API keys
wispa lets you bring your own API keys for cloud transcription and AI cleanup. Keys are stored on your device, and you stay in control.
3 min readSetting up a cloud key
Get a key from your provider, paste it into wispa's Cloud keys section, and use the built-in test to confirm it works.
3 min readSupported providers
wispa works with several cloud providers. Two of them transcribe, and all of them can run the optional AI cleanup step.
2 min readModes and cleanup
Named setups that pick a model, a language and optional AI cleanup for each kind of writing.
Dictation modes
A mode is a named setup that decides how a recording is transcribed and styled. Keep one per kind of writing and switch in a tap.
2 min readCreating and editing modes
Build a mode from a template, set its model and optional cleanup, save it, and switch to it from the tray, the mode switcher or the header.
3 min readAI text cleanup
An optional per-mode step sends your transcript to an AI model to drop filler and format it. A deterministic filler removal runs first, no key needed.
3 min readCommands and agents
Turn speech into actions, and talk to coding agents like Claude Code and Codex.
Voice commands
Command mode is a second hotkey that runs actions from your voice instead of inserting text. Nothing is typed, and nothing is saved to history.
3 min readCreating voice commands
Start from a template, set a trigger phrase, and choose what the command does. Types range from opening an app to running a script.
3 min readVoice for coding agents
wispa can drive terminal coding agents by voice, so when Claude Code or Codex pauses to ask, you answer out loud instead of typing.
2 min readReady when you are
Start dictating in minutes
Download wispa, load a model or add a cloud key, and your voice becomes clean text in nearly any app. Free while in beta.
Download wispa