# wispa

> wispa is an AI voice-to-text dictation app for macOS. Hold a shortcut, speak, and clean, finished text is typed into nearly any app with a standard text field. Transcription can run fully on-device with local models, so your voice and text can stay on your Mac. Free trial of up to 8,000 words (5,000 plus optional feedback), then a one-time €39 lifetime license. No account required.

Press and hold a global hotkey (default Option+Space), dictate, and release: wispa transcribes your speech and can optionally clean it up with AI into finished text, then pastes it where you are typing. Speech-to-text can run locally with Whisper models (plus Parakeet on Apple Silicon) for privacy, or you can bring your own cloud API key (OpenAI or Groq). The optional AI clean-up step also uses your own key. A separate Command mode lets you speak an action instead of inserting text, and wispa carries it out.

Try wispa free for up to 8,000 words (5,000 base, plus 3,000 once for optional feedback), then a one-time €39 lifetime license on up to 3 Macs. No account or sign-up required. It runs on macOS 13+ (Apple Silicon). The site is available in English (default) and localized in German, Spanish and French.

For the full text of every page in one file (all help articles inlined), see [/llms-full.txt](https://wispa.it/llms-full.txt).

## Product
- [wispa — overview, features and FAQ](https://wispa.it/): AI voice dictation for Mac. Hold a key, speak, and clean text lands in nearly any app. Transcription can stay on your Mac. Free trial, no account.
- [Mac Voice-to-Text Dictation for Apple Silicon](https://wispa.it/mac/): AI voice dictation for your Mac. Hold a key, speak, and clean text lands in nearly any app. Built for Apple Silicon, on-device with Whisper. Free trial, no account.
- [wispa for Claude Code](https://wispa.it/claude-code/): Claude Code runs long, then stops to ask. wispa opens a reply window where you work, so you answer by voice — straight back into the session.
- [wispa for Codex](https://wispa.it/codex/): Codex pauses for approvals and questions. wispa opens a reply window where you work, so you answer by voice — straight back into the session.
- [wispa for Antigravity](https://wispa.it/antigravity/): Antigravity asks from the terminal; wispa answers over any app. A reply window opens where you work, you speak, and it lands back in the session.
- [wispa for Cursor](https://wispa.it/cursor/): Cursor's agent ranges across your codebase, then stops on the calls that matter. wispa opens a reply window so you answer by voice.
- [wispa for OpenCode](https://wispa.it/opencode/): OpenCode runs long build loops in your terminal, then stops for a call. wispa opens a reply window where you work, so you answer by voice.
- [wispa for Pi](https://wispa.it/pi/): Pi runs a lean agent loop in your terminal and checks in often. wispa opens a reply window where you work, so you answer by voice.
- [Download wispa](https://github.com/Miotares/wispa-releases/releases/latest): Latest macOS build via GitHub Releases.

## Help center
- [Help center](https://wispa.it/help/): Guides, how-tos and answers for installing and using wispa.
- [How wispa works](https://wispa.it/help/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.
- [Installing wispa](https://wispa.it/help/install-wispa/): Download wispa for your Mac, open it once, and grant two quick permissions so it can hear you and type for you.
- [Keyboard shortcuts](https://wispa.it/help/keyboard-shortcuts/): wispa is driven by a few global hotkeys. Here are the defaults and how holding differs from tapping.
- [Troubleshooting](https://wispa.it/help/troubleshooting/): The handful of things that trip people up, and how to fix each one in a minute.
- [Transcription models](https://wispa.it/help/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.
- [Local vs cloud models](https://wispa.it/help/local-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.
- [Which model should I choose?](https://wispa.it/help/which-model-to-choose/): Pick a model by what matters most to you, privacy, speed, accuracy or a light footprint. Here is a cheat sheet.
- [Downloading and managing models](https://wispa.it/help/download-and-manage-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.
- [Languages](https://wispa.it/help/dictation-languages/): wispa transcribes dozens of languages through Whisper, and its own interface comes in English, German, Spanish and French.
- [Cloud API keys](https://wispa.it/help/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.
- [Setting up a cloud key](https://wispa.it/help/set-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.
- [Supported providers](https://wispa.it/help/supported-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.
- [Local AI cleanup with Ollama or LM Studio](https://wispa.it/help/local-ai-cleanup/): 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.
- [Dictation modes](https://wispa.it/help/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.
- [Super mode](https://wispa.it/help/super-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.
- [Creating and editing modes](https://wispa.it/help/create-and-edit-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.
- [AI text cleanup](https://wispa.it/help/ai-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.
- [Record and summarize meetings](https://wispa.it/help/record-meetings/): Beyond dictation, wispa records long meetings from your mic and the app audio, transcribes them, labels who spoke, and writes an AI summary you can export.
- [Voice commands](https://wispa.it/help/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.
- [Creating voice commands](https://wispa.it/help/create-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.
- [Voice for coding agents](https://wispa.it/help/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.
- [Voice for Claude Code](https://wispa.it/help/voice-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.
- [Voice for Codex](https://wispa.it/help/voice-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.
- [Voice for Cursor](https://wispa.it/help/voice-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.
- [Voice for Antigravity](https://wispa.it/help/voice-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.
- [Voice for OpenCode](https://wispa.it/help/voice-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.
- [Voice for Pi](https://wispa.it/help/voice-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.

## Free browser tools
- [Free tools](https://wispa.it/tools/): Free browser tools from wispa: test your mic, record your voice, and measure your typing speed. No signup, and nothing leaves your device.
- [Typing Speed Test](https://wispa.it/tools/typing-speed-test/): Free typing speed test. Type a short passage to see your live words-per-minute and accuracy, then how much faster your voice is. No signup, in your browser.
- [Mic Test](https://wispa.it/tools/mic-test/): Free online mic test. Check your mic with a live waveform and level meter, then record a few seconds and play it back. Your audio never leaves your browser.
- [Online Voice Recorder](https://wispa.it/tools/voice-recorder/): Free online voice recorder. Record straight from your browser, play it back, and download a WAV. Nothing is uploaded or stored. Up to 10 minutes per take.

## Other languages
- [Deutsch](https://wispa.it/de/) · [Español](https://wispa.it/es/) · [Français](https://wispa.it/fr/)