Your first transcript

Start with a short recording using a local speech model. You can add AI cleanup or a remote engine once the basic recording works.

1. Install and open OpenWhisper#

Follow Installation for your platform. On macOS, approve the first launch and allow Microphone access.

2. Choose a speech engine#

Open Settings → Voice model. New Windows x64 installations default to Parakeet; other platforms default to Local Whisper. Existing installations keep your previous choice.

Keep the default for this first recording, or use Choosing a model to compare alternatives. A local speech engine does not require a cloud API key.

3. Download the model#

Open Settings → Downloads and install the selected model and any required runtime. Wait for the downloads to finish before recording.

Model weights and runtimes are separate components. If an engine still needs a component, return to Downloads and check its requirements.

4. Select your microphone#

Open Settings → Recording and choose the microphone you want to use. For the first test, use the app's recording button so you can confirm the microphone and model independently of global shortcuts.

5. Record a few sentences#

In Quick Record, start recording, speak a short sentence, and stop. OpenWhisper transcribes the audio when you stop; supported engines also show a live preview while you speak.

For example, say: “This is my first OpenWhisper recording. I am checking that my microphone works.”

6. Use the finished text#

Copy the result from Quick Record. Dictation follows your clipboard and auto-paste settings. To send text into another app automatically, enable auto-paste in Settings → General and grant Accessibility permission on macOS.

Before relying on auto-paste, try a recording in a text editor. Leave the intended destination focused while the recording finishes.

Make it your own#

• Set a recording shortcut in Settings → Hotkeys. Choose Toggle or Push and hold.
• Turn on AI cleanup for punctuation, spelling rules, or output profiles.
• Use Upload File for an existing recording. Its results stay in the app with Copy buttons.
• Download everything you need before going offline. See Privacy & offline.

If you get silence, a model error, or no pasted text, use Troubleshooting to check the relevant step.