Turn your voice into text

1. Click Done (not Move to Trash).
2. Open System Settings → Privacy & Security and scroll to the bottom.
3. Next to “Astrocat was blocked”, click Open Anyway, then enter your Mac password.
4. Open Astrocat again and click Open. You only do this once.

On macOS 15 (Sequoia) and later, right-click → Open no longer works for this. Use the System Settings button above.

It isn't damaged: macOS adds a download flag. Open Terminal (Cmd+Space, type Terminal), paste this line and press Enter:

xattr -cr /Applications/Astrocat.app

Then open Astrocat from Applications as normal.

Astrocat needs Accessibility permission to type into other apps.

1. Quit Astrocat.
2. Open System Settings → Privacy & Security → Accessibility.
3. If Astrocat is listed, select it and click − to remove it.
4. Click +, choose Astrocat from Applications, and make sure its switch is on.
5. Open Astrocat again.

Do this again after every Astrocat update: macOS treats the new version as a new app, even though the old one still shows as switched on.

1. Settings → Shortcuts: set your key on the Global tab. The Local tab only works inside the Astrocat window.
2. Keep Astrocat running: close the window, but don't quit it. You'll see it in the menu bar at the top of the screen.
3. Do the Accessibility steps above. Also check Privacy & Security → Input Monitoring: if Astrocat is listed, switch it on.
4. Use Control or Cmd in your shortcut. Since macOS 15, shortcuts that use only Option (or Option + Shift) as the modifier are blocked for apps like this.
5. Still stuck? Restart the Mac once after changing permissions.

Open System Settings → Privacy & Security → Microphone and switch Astrocat on. Then pick your microphone in Astrocat's Settings → Recording.

By default, no. Everything is stored locally. Audio is only sent to the transcription provider you connect via API key (e.g. Groq or OpenAI), and only directly from your device, with no middleman servers.

Plain text, with optional transformations for grammar fixes, translation, or formatting.

It is optimized for short, fast transcriptions. For longer sessions, we recommend a dedicated recording app.

Yes. You can set up AI transformations to automatically format your text, fix grammar, or translate languages.

How to set up Transformations:

1. Go to Transformations.
2. Click Create Transformation.
3. Add a Processing Step: set the dropdown to Prompt Transform, select your preferred AI provider (e.g. Groq or OpenAI), then add your System Prompt and User Prompt.
4. Create the transformation, click the edit icon, and select the “run on future transcriptions” option at the bottom right.

Sample system prompt:

You are an intelligent text formatter specializing in cleaning up transcribed speech. Your task is to transform raw transcribed text into well-formatted, readable content while maintaining the speaker's original intent and voice.

Core Principles:
- Preserve authenticity: Keep the original wording and phrasing as much as possible
- Add clarity: Make intelligent corrections only where needed for comprehension
- Enhance readability: Apply proper formatting, punctuation, and structure

Formatting Guidelines:

Punctuation & Grammar:
- Add appropriate punctuation (periods, commas, question marks)
- Correct obvious transcription errors while preserving speaking style
- Fix run-on sentences by adding natural breaks
- Maintain conversational tone and personal speaking patterns

Structure & Organization:
- Create paragraph breaks at natural topic transitions
- Use bullet points or numbered lists when the speaker is listing items
- Add headings if the content has clear sections
- Preserve emphasis through italics or bold when the speaker stresses words

Intelligent Corrections:
- Fix homophones (e.g., "there/their/they're")
- Complete interrupted thoughts when the intention is clear
- Remove excessive filler words (um, uh) unless they add meaning
- Correct obvious misspeaks while noting significant ones in [brackets]

Special Handling:
- Technical terms: Research and correct spelling if unclear
- Names/places: Make best guess and mark uncertain ones with [?]
- Numbers: Convert spoken numbers to digits when appropriate
- Time references: Standardize format (e.g., "3 PM" not "three in the afternoon")

Preserve Original Intent:
- Keep colloquialisms and regional expressions
- Maintain the speaker's level of formality
- Don't "upgrade" simple language to sound more sophisticated
- Preserve humor, sarcasm, and emotional tone

Output Format: Return the formatted text with:
- Clear paragraph breaks
- Proper punctuation and capitalization
- Any structural elements (lists, headings) that improve clarity
- [Bracketed notes] for unclear sections or editorial decisions
- Original meaning and voice intact

Remember: You're a translator from spoken to written form, not an editor trying to improve the content. Make it readable while keeping it real.

Sample user prompt:

Here is the text to format: {{input}}

Astrocat Whispering supports Groq, OpenAI, and faster-whisper-server.

Yes, using the faster-whisper-server transcription service.

faster-whisper-server setup: Ensure Docker or an equivalent (e.g. Orbstack) is installed, then run one of the following in your terminal.

CPU Mode, for computers without CUDA support:

docker run -e ALLOW_ORIGINS='["<https://whispering.bradenwong.com>"]' --publish 8000:8000 --volume ~/.cache/huggingface:/root/.cache/huggingface fedirz/faster-whisper-server:latest-cpu

GPU Mode, for computers with CUDA support:

docker run -e ALLOW_ORIGINS='["<https://whispering.bradenwong.com>"]' --gpus=all --publish 8000:8000 --volume ~/.cache/huggingface:/root/.cache/huggingface fedirz/faster-whisper-server:latest-cuda

Svelte 5 + Tauri: lightweight, fast, and open source under the MIT License.