How to set Voice service in Ozeki Voice Keyboard

This guide demonstrates how to configure the Voice service used by Ozeki Voice Keyboard for speech-to-text transcription. You will learn how to access the Voice model settings through the system tray icon and enter your API URL and API key to connect to your chosen speech recognition service.

How does it work

The diagram below illustrates how Ozeki Voice Keyboard works. In short the software makes a voice recording. It send this audio file to the Voice Service (Speech Detector, which uses the Whisper AI model for transcription) and the Speech detector service returns the transcription as text.

sequenceDiagram participant Human participant SpeechDetector as Speech Detector Human->>SpeechDetector: Voice Input (audio) SpeechDetector-->>Human: Transcription (text)

How to configure your Voice service video

The following video shows how to set the Voice service in Ozeki Voice Keyboard step-by-step. The video covers locating the tray icon, opening the Voice model settings, and entering the connection details for your speech recognition service.

Step 1 - Find the Voice Keyboard tray icon

Ozeki Voice Keyboard runs in the background and can be accessed through the Windows system tray in the bottom right corner of your taskbar. If you do not see the icon, click the arrow to expand the hidden tray icons (Figure 1).

Figure 1 - Find the Voice Keyboard tray icon

Step 2 - Open Voice model settings

Right-click the Ozeki Voice Keyboard tray icon to open the context menu. From the menu, select the Voice settings option to open the configuration window where you can enter your speech recognition service connection details (Figure 2).

Open Voice model settings from context menu — Figure 2 - Open Voice model settings from the context menu

The Voice model settings window is used to configure the speech-to-text service that processes your voice recordings. The service uses an OpenAI-compatible endpoint, meaning it works with OpenAI Whisper speech recognition service. Here you can specify the API endpoint URL and the API key for authentication (Figure 3).

Figure 3 - Ozeki Voice Keyboard Voice model settings window

Step 3 - Enter API URL, model and API key

Fill in the required fields with your speech recognition service connection details. Enter the API endpoint URL of your Whisper-compatible service, specify the model name you want to use for transcription, and paste in your API key (Figure 4).

Step 4 - Save Voice settings

Once you have filled in all the required fields, click OK to save the configuration. The Voice service is now ready to use - simply place your cursor in any input field, hold the Ctrl + Alt keys to record your voice, and after releasing the keys the audio will be sent to your configured service for transcription (Figure 5).

Click OK to save settings — Figure 5 - Click OK to save the settings

Final thoughts

You have successfully configured the Voice service for Ozeki Voice Keyboard. The application will now use your specified speech recognition endpoint to transcribe your voice recordings, giving you the flexibility to connect to OpenAI's Whisper service, a self-hosted model, or any other compatible provider.