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. Hold a key, speak, and your words are typed into whatever app you are using.
3 min readInstalling wispa
Download wispa for your Mac, 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 providers. Two transcribe your dictation in the cloud, one handles meetings, and the rest run the optional AI cleanup step, which can also run locally.
2 min readLocal AI cleanup with Ollama or LM Studio
wispa's AI cleanup does not have to use the cloud. Run it through Ollama or LM Studio and the whole step stays on your device, with no key and no internet.
3 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 readSuper mode
Super mode is a built-in macOS mode that reads the app around you to clean up dictation, and when you select text first, your speech becomes an instruction on it.
3 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 menu bar, 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 readMeetings
Record a meeting from your mic and system audio, label the speakers, and get an AI summary.
Voice commands
Turn speech into actions: open an app, run a shell command or switch mode, all by voice.
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 readCoding agents
Answer terminal coding agents by voice. Claude Code, Codex, Cursor, Antigravity, OpenCode and Pi, with a guide for each.
Voice 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 readVoice for Claude Code
wispa adds a voice loop to Claude Code in the terminal: when Claude Code stops to ask you something, you answer out loud and your words go back as its next message.
3 min readVoice for Codex
wispa adds a voice loop to the Codex CLI: when Codex finishes a turn and waits for you, you answer out loud and your words go back as its next message.
3 min readVoice for Cursor
wispa adds a voice loop to Cursor, in the terminal and in the Cursor editor: when the agent stops to ask, you answer out loud and Cursor submits your words as the next message.
3 min readVoice for Antigravity
wispa adds a voice loop to the Antigravity CLI: when the agent stops to ask, you answer out loud and your words go back as its next message.
3 min readVoice for OpenCode
wispa adds a voice loop to OpenCode with a small plugin: when OpenCode finishes and goes idle, you answer out loud and your words are sent back as the next message.
3 min readVoice for Pi
wispa adds a voice loop to the Pi coding agent with a small extension: when Pi finishes a turn, you answer out loud and your words go back as the next message.
3 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