Does it work without an internet connection?

Yes. Transcription runs entirely on your machine using the local model you've downloaded. Once the model is cached, no network connection is required.

What do I get when I buy?

You get compiled installers for all 3 platforms: Linux (.AppImage), macOS (.dmg), and Windows (.exe). No Python installation required — just download and run.

What's the difference between Free and Pro?

Free includes the base model and 7-day trial with all features. Pro ($19/mo or $190/yr) unlocks all local models, unlimited history, dictionary persistence, full stats, and priority support.

FAQ and Troubleshooting

Frequently Asked Questions

Where do I enter my license key?

Open the Agent Wispr Settings → About tab. Paste your key and click Activate. Your key was included in the purchase confirmation email. See Activating Pro for detailed steps.

I have a promo code -- where do I use it?

On the Buy page, click Buy Now. A promo code field appears on the Stripe checkout page before you enter payment details.

Does it work without internet?

Yes. Transcription happens 100% locally on your machine. An internet connection is only needed during the first run to download your selected Wispr model, and for the optional AI Cleanup (Groq) feature.

Where is my audio stored?

Nowhere. Audio is processed in memory and deleted immediately after transcription. We value your privacy and never upload your voice data to any server.

How do I use it with Claude Code or Cursor?

Just focus the terminal or editor where you want to type, hold the hotkey, and speak. Agent Wispr injects the text exactly as if you had typed it on your keyboard.

It's not typing into my terminal!

If you are running your terminal (like PowerShell or CMD) as Administrator, you must also run Agent Wispr as Administrator. Windows security prevents non-admin apps from sending keystrokes to admin apps.

Troubleshooting

"No Microphone Detected"

Open Settings → Microphone and select the input device you want to use.
Click Test to confirm the app is receiving audio.
On macOS, check System Settings > Privacy & Security > Microphone and make sure Agent Wispr is allowed. Quit and reopen the app after changing permissions.
If you are still on an older build, delete it and install the latest release from agentwispr.agentsoftware.dev/demo.
If you are on Linux or WSL and no devices appear, verify your OS exposes an input device before launching Agent Wispr.

Transcription is slow

If you have an NVIDIA GPU, ensure the Processing Device is set to CUDA in the Model settings.
Try a smaller model size (e.g., base or tiny) for faster processing on older hardware.

App is "Already Running"

Check your system tray (Windows) or menu bar (Linux/macOS). Agent Wispr runs as a background process and can be accessed via its floating widget.