Table of Contents

Introduction to Ozeki Voice Keyboard

Ozeki Voice Keyboard is a Windows application that allows you to type text using only your voice. Simply hold down Ctrl + Alt, speak into your microphone, and release the hotkey—the transcribed text will be automatically pasted into the active window. This guide gives you a short introduction on how Ozeki Voice Keyboard works.

Main features:

• Ctrl + Alt - Send the dictated text to your app
• Ctrl + Space - Send the dictated text to AI for processing and type the result into your app
• Win + Space - Send your clipboard contents to AI for processing and type the result to your app

How does it work

The diagram below illustrates how Ozeki Voice Keyboard works.

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

See it in action

View the following video to see Ozeki Voice Keyboard in action:

How to make it smarter:
- Write your own system prompt. (Select system prompt from the popup menu in the tray icon)

How can you use it

• Step 1 - Launch Ozeki Voice Keyboard
• Step 2 - View hotkeys in the bottom right corner
• Step 3 - Use the hotkey for transcription
• Step 4 - Ask the AI assistant a question

Step 1 - Launch Ozeki Voice Keyboard

Launch the Ozeki Voice Keyboard application on your Windows system. Once started, the application runs in the background and is always ready to capture your voice input without interfering with your other open applications (Figure 1).

Step 2 - View hotkeys in the bottom right corner

After launching, a small overlay appears in the bottom right corner of your screen showing the available hotkeys. This gives you a quick reference for both features (voice transcription and the AI assistant) without having to open any menus (Figure 2).

Step 3 - Use the hotkey for transcription

Click into any input field or document where you want to insert text, then press and hold Ctrl + Alt. The application will record your voice for as long as the keys are held down, so speak clearly into your microphone and release them only when you have finished (Figure 3).

After releasing the keys, the recorded audio is sent to the speech recognition model for transcription. A brief processing indicator will appear while your recording is being analyzed and converted to text (Figure 4).

Once transcription finishes, the resulting text is automatically pasted into the input field that was active when you started recording. No manual copying or pasting is required - the text appears instantly in your textbox, document, or any other field that was selected, exactly as if you had typed it with a keyboard (Figure 5).

Step 4 - Ask the AI assistant a question

The following video shows how to use the AI assistant feature of Ozeki Voice Keyboard.

Place your cursor in any input field where you want the response to appear, then press Ctrl + Space and speak your question into the microphone. In this example, the AI is asked to generate a code snippet for calculating Fibonacci numbers (Figure 6).

After releasing the keys, the question is sent to the configured AI model for processing. You will see a brief indicator while the model generates its response (Figure 7).

Once the model finishes, the response is automatically typed into the active input field. In this example, the AI generated a code snippet, which was pasted into the editor without any manual intervention (Figure 8).

Final thoughts

You have successfully learned how to use both features of Ozeki Voice Keyboard on Windows. Whether you need to quickly dictate text or generate AI-powered responses, both tools work entirely hands-free and deliver results directly into any input field on your system.

Ozeki Voice Keyboard Screenshots

T-MOBILE-CZ VPN SETUP

on Fedora Core 3 Linux

This guide gives you detailed steps to help you configure the VPN connection to Vodafone Hungary. Before starting the configuration, make sure you have the following information:

Ozeki Voice Keyboard Features

Ozeki Voice Keyboard Datasheet

Ozeki Voice Keyboard System Requirements

This page lists the minimum and recommended system requirements for running Ozeki Voice Keyboard on Windows. The application is lightweight and runs on most modern Windows systems without any additional hardware requirements.

Operating system

Ozeki Voice Keyboard runs on Windows 10 and Windows 11. It is built on .NET 10 for Windows and uses Windows Forms for its user interface. No additional runtime installation is required as the necessary components are bundled with the installer.

Hardware requirements

The table below lists the minimum and recommended hardware specifications for running Ozeki Voice Keyboard.

The IP address of the T-mobile-cz SMSC:	88.77.66.128

Component	Minimum	Recommended
CPU	Any dual-core x64 processor	Quad-core x64 processor or better
RAM	256 MB available	512 MB or more
Storage	128 MB free disk space	256 MB free disk space
Microphone	Any microphone or audio input device	Dedicated headset or microphone

Network requirements

Ozeki Voice Keyboard communicates with external AI services over HTTP. An internet connection is required when using cloud-based speech recognition or LLM providers. If both the voice transcription model and the LLM are hosted locally on your network, the application can operate fully offline without any internet access.

AI service requirements

For voice transcription, any OpenAI-compatible /v1/audio/transcriptions endpoint is supported, including OpenAI Whisper and self-hosted Whisper instances. For the AI assistant feature, any OpenAI-compatible /v1/chat/completions endpoint is supported, including cloud providers and locally hosted LLMs such as Ollama or LLama.cpp.

Software dependencies

Ozeki Voice Keyboard has no external software dependencies that require manual installation. All required libraries are bundled within the installer package.

Ozeki Voice Keyboard Screenshots

Explore Ozeki Voice Keyboard in action. The screenshots below provide a visual overview of the application's key features, including voice transcription, the AI assistant, microphone and model configuration, and the hotkey settings panel.

Figures 1 and 2 show the two core features of Ozeki Voice Keyboard - voice-to-text transcription and the AI assistant. Figures 3 to 7 show the various configuration windows available through the system tray context menu.

Ozeki Voice Keyboard Features

Voice transcription

• Speech-to-text transcription: Hold Ctrl + Alt to begin recording, then release to transcribe. The resulting text is inserted directly into the active input field: whether a text editor, browser field, or any other application that accepts keyboard input.
• Microphone selection: Select the audio input device used for recording from the microphone settings window. Ozeki Voice Keyboard enumerates all input devices detected on the system, allowing you to switch between a headset, built-in microphone, or any other connected audio source.
• Voice model configuration: Configure the speech recognition endpoint through the Voice settings window. Ozeki Voice Keyboard supports any OpenAI-compatible API, including OpenAI Whisper, self-hosted Whisper instances, and third-party providers. The API URL, model name, and API key are all adjustable.

AI assistant

• Voice-activated AI assistant: Hold Ctrl + Space to activate the AI assistant. Upon releasing the keys, the spoken input is transcribed and submitted to the configured LLM as a prompt. The generated response is typed directly into the active input field.
• LLM service configuration: Connect to any OpenAI-compatible LLM endpoint through the LLM settings window. Supported backends include cloud-based providers, locally hosted models such as Ollama or LLaMA.cpp, and Ozeki AI Gateway for centralized access management. The API URL, model name, and API key are all configurable.
• System prompt editor: Define a system prompt that is included with every AI request. Use this to control the assistant's tone, scope, and response style to match your specific workflow or use case.

Hotkey settings

• Configurable hotkeys: Reassign the keyboard shortcuts for voice recording and AI assistant activation through the hotkey settings panel. This is useful when the default key combinations conflict with other applications installed on your system.
• Hotkey overlay: A small overlay displayed in the bottom-right corner of the screen shows the active hotkeys when Ozeki Voice Keyboard starts. This provides a quick visual reference without requiring you to open any settings window.

Integration and compatibility

• Works with any input field: Transcribed and AI-generated text is inserted into whichever input field is active at the time of the request. Ozeki Voice Keyboard is compatible with text editors, browsers, IDEs, chat applications, and any other Windows application that accepts keyboard input.
• Ozeki AI Gateway integration: Both voice transcription and AI assistant requests can be routed through Ozeki AI Gateway, giving organizations centralized control over API access, model selection, usage monitoring, and authentication across multiple client machines.
• OpenAI-compatible API support: Ozeki Voice Keyboard works with any service that implements the OpenAI API format, including third-party cloud providers and locally hosted models. This makes it straightforward to switch providers or operate the application fully offline using local speech recognition and LLM services.
• HTTP request logging: Enable HTTP logging from the tray icon context menu to monitor outgoing API requests in real time. This is useful for verifying that requests are reaching the intended endpoint and for diagnosing connection issues with configured AI services.

Ozeki Voice Keyboard Datasheet

This page provides a complete technical overview of Ozeki Voice Keyboard, including product details, system requirements, supported protocols, and feature specifications.

Product information

Product name	Ozeki Voice Keyboard (OzKey)
Category	Speech-to-text and AI assistant application for Windows
Product website	ozekivoice.com
Package content	OzKey_x.x.x.zip (contains the Windows installer executable)
Main task	Enables hands-free text input and AI-assisted content generation by transcribing voice recordings and forwarding prompts to configured AI services, with results automatically inserted into the active input field.

Technology

Underlying technology	C# (.NET 10.0-windows)
User interface	Windows Forms (system tray application)
Operation mode	Background Windows application, accessible via system tray
Application type	Windows executable (.exe)
Supported operating systems	Microsoft Windows 10 Microsoft Windows 11

API connectivity

Voice transcription endpoint	Any OpenAI-compatible /v1/audio/transcriptions endpoint, including: OpenAI Whisper (cloud) Self-hosted Whisper via agent-cli (Windows native, WSL) Self-hosted Whisper via vLLM (Ubuntu) Ozeki AI Gateway
LLM endpoint	Any OpenAI-compatible /v1/chat/completions endpoint, including: OpenAI (cloud) Ollama (local, Windows) LLama.cpp (local, Ubuntu) vLLM (local, Ubuntu) Ozeki AI Gateway
Authentication	API key passed as Bearer token in the Authorization header
Transport protocol	HTTP / HTTPS

GUI layout

Components	System tray icon with right-click context menu Hotkey overlay displayed in the bottom-right corner of the screen Microphone selection window Voice model settings window LLM settings window System prompt editor Hotkey settings panel HTTP log viewer
Accessibility	All configuration windows are accessible with a single right-click on the system tray icon.

Installation and removal

Installation method	Download ZIP from ozekivoice.com, extract the archive, and run the installer executable.
Uninstallation method	Via Windows Installed Apps list using the built-in uninstaller, or manually by removing the application files, Start Menu entry, desktop shortcut, and registry key.
Installation size	112 MB (installer package: ~45 MB compressed)

Ozeki Voice Keyboard User Guide

This article provides configuration guides for Ozeki Voice Keyboard, a voice input application that enables speech-to-text transcription and AI-powered assistance. The guides cover essential setup steps including microphone selection, LLM service configuration, and voice service setup. Whether you're setting up voice input for the first time or optimizing your existing configuration, these step-by-step guides walk you through each process with clear instructions.

How to select the Microphone in Ozeki Voice Keyboard

Learn to select and configure your preferred microphone for Ozeki Voice Keyboard. Access settings via the system tray icon and choose from available audio input devices. Save your selection to enable voice recording and transcription for optimal speech recognition accuracy.

How to select the Microphone in Ozeki Voice Keyboard

How to setup LLM service in Ozeki Voice Keyboard

Configure the AI assistant by setting up your LLM service connection. Access settings through the system tray, enter your API URL, select a model, and provide your API key. Works with any OpenAI-compatible endpoint for AI-powered assistance.

How to set up your LLM service in Ozeki Voice Keyboard

How to setup Voice service in Ozeki Voice Keyboard

Set up speech-to-text transcription by configuring the Voice service. Access settings via the system tray, enter your Whisper-compatible API endpoint, specify the model, and add your API key. Your voice input will be automatically transcribed.

How to set up your Voice detection service in Ozeki Voice Keyboard

Ozeki Voice Keyboard for Business

Get the business license for full on-premises deployment with central configuration and management. Includes local AI models, cloud integration, security features, technical support, high availability, and team management tools with no installation limits.

Ozeki Voice Keyboard for Business

How to improve productivity with Ozeki Voice Keyboard

Discover tips and techniques to boost your productivity using voice input and AI assistance features in Ozeki Voice Keyboard.

How to improve productivity with Ozeki Voice Keyboard

Ozeki Voice Keyboard - Configuration Guides

This section contains comprehensive guides for configuring and using Ozeki Voice Keyboard, including microphone selection, LLM service setup, voice service configuration, business licensing options, and productivity enhancement tips.

How to select the Microphone in Ozeki Voice Keyboard

This guide demonstrates how to select and configure the microphone used by Ozeki Voice Keyboard. You will learn how to access the microphone settings through the system tray icon and choose your preferred input device from the available list.

Steps to follow

1. Find the Voice Keyboard tray icon
2. Open microphone settings
3. Choose preferred microphone
4. Save microphone settings

How to select the microphone video

The following video shows how to select the microphone in Ozeki Voice Keyboard step-by-step. The video covers locating the tray icon, opening the microphone settings, and selecting your preferred input device.

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).

Step 2 - Open microphone settings

Right-click the Ozeki Voice Keyboard tray icon to open the context menu. From the menu, select the microphone settings option to open the microphone configuration window (Figure 2).

The microphone selection window lists all audio input devices currently available on your system. This includes any built-in microphones, USB microphones, headsets, or other recording devices that are connected and recognized by Windows (Figure 3).

Step 3 - Choose preferred microphone

Click the dropdown list to see all available microphone devices and select the one you want Ozeki Voice Keyboard to use for recording. Choose the device that best suits your setup - for example, a dedicated USB microphone or headset will generally produce better transcription results than a built-in laptop microphone (Figure 4).

Step 4 - Save microphone settings

Once you have selected your preferred microphone, click OK to save the configuration. Ozeki Voice Keyboard will now use the selected device for all future voice recordings. You can return to this settings window at any time to switch to a different microphone if needed (Figure 5).

To sum it up

You have successfully configured the microphone for Ozeki Voice Keyboard. The application will now use your selected input device when recording voice for transcription, helping ensure the best possible speech recognition accuracy for your setup.

How to set LLM service in Ozeki Voice Keyboard

This guide demonstrates how to configure the LLM service used by Ozeki Voice Keyboard for its AI assistant feature. You will learn how to access the LLM API settings through the system tray icon and enter your API URL, model, and API key.

Steps to follow

1. Find the Voice Keyboard tray icon
2. Open LLM API settings
3. Enter API URL, AI model and API key
4. Save LLM settings

How to set your LLM service video

The following video shows how to set the LLM service in Ozeki Voice Keyboard step-by-step. The video covers locating the tray icon, opening the LLM API settings, and entering the connection details for your chosen AI 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).

Step 2 - Open LLM API settings

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

The LLM settings window is used to configure the AI assistant feature of Ozeki Voice Keyboard. When you press Ctrl + Space, your question is sent to this service and the response is typed directly into your active input field. Here you can specify the API endpoint URL, the model, and the API key for authentication (Figure 3).

Step 3 - Enter API URL, AI model and API key

Fill in the required fields with your LLM service connection details. Enter the API endpoint URL, specify the model name, and paste in your API key. Ozeki Voice Keyboard is compatible with any OpenAI-compatible endpoint, including local models and third-party providers (Figure 4).

Step 4 - Save LLM settings

Once you have filled in all the required fields, click OK to save the configuration. The AI assistant is now ready to use - simply place your cursor in any input field, press the hotkey, and the response will be typed out automatically (Figure 5).

Conclusion

You have successfully configured the LLM service for Ozeki Voice Keyboard. The application will now use your specified AI service and model when you press Ctrl + Space to ask a question, typing the AI's response directly into your active input field. You can connect to any compatible API endpoint, including local or cloud-based AI providers.

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.

Steps to follow

1. Find the Voice Keyboard tray icon
2. Open Voice model settings
3. Enter API URL, model and API key
4. Save Voice settings

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).

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).

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).

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).

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.

Ozeki Voice Keyboard for Business

If you run a business, and you wish to make your employees more efficient with Ozeki Voice Keyboard, you might be interested in the Ozeki Voice Keyboard for Business license.

What is included in the Ozeki Voice Keyboard for Business Lincense

• Full on-premises deployment: Ozeki Voice Keyboard will work inside your own network. Your voice recordings and your AI requests will stay in your own environment.
• Centeral configuration: You can setup a settings.json file, on one of your http servers. On startup all of your computers with Ozeki Voice Keyboard installed will connect to it, to download your settings.
• Centeral management and trouble shooting: Ozeki Voice Keyboard clients can be mangaged from a centeral server, access can be granted / revoked to individual clients. Logs can be turned on for trouble shooting purposes.
• Local AI models: You can setup a local AI transcriber to serve the Ozeki Voice Keyboard transcription requests. This way no data will leave your network. You can also connect to local Large Language Models (LLMs), served by vllm, sglang, llama.cpp, ollama or other AI inference engiens to provide AI responses
• Cloud models: You can connect your system to cloud services, such as OpenAI ChatGPT, Anchropic Claud, Google Gemini and others. You can use your API keys for such services in a safe way.
• Safety and security: Your API keys will not be exposed, they will stay safe on your centeral configuration server, and individual access tokens will be generated to clients. You will have the ability to restrict client access.
• Technical support: You can get technical support for your system. You can open support tickets, chat with Ozeki engineers and make calls to our support team on the phone. Please check the technical support service levels available.
• High availability: AI model routing can be setup, to provide high availability. The centeral server can switch over to other AI servies in case AI service failure. (Backup routes can be set up).
• Team managemenet: Custom system prompts can be defined to boost productitvity for teams and individuals. This allows tailored AI responses depending on job requirements.

How manu employees / workstations are supported

The Ozeki Voice Keyboard Business Edition has no limitation for the number of installations. Ozeki Voice Keyboard is very resource efficient. You can serve tens of thousands of workstations from a single AI server.

Will I get technical support?

You can purchase standard technical support for 500,- EUR / year for Ozeki Voice Keyboard. This will enable you to open technical support tickets at our support portal: https://myozeki.com. You may subscribe for higher level technical support packages.

An ongoing technical support subscription also entitles you to get the latest Ozeki Voice Keyboard software versions for your organizations. Ozeki release version updates regularly.

How much does it cost

One time license fee: EUR 3000,-
Annual technical support (optional): EUR 1000,-/year

How to purchase a license

Send an e-mail to info@ozeki.hu, and let us know, that you are interested in purchasing a business license. We will send you a proforma invoice, and once the license fee is stransfered, you will get download instructions for the business version in e-mail.

How to improve productivity with Ozeki Voice Keyboard

Discover powerful techniques to enhance your workflow with Ozeki Voice Keyboard. Learn how to customize system prompts for faster AI responses and configure personalized keyboard shortcuts to streamline your productivity experience.

How to set up a custom system prompt

Learn to configure personalized system prompts that streamline your AI interactions in Ozeki Voice Keyboard. Define behavior, tone, and output format to receive consistently formatted, relevant responses without repeating context on every request. Perfect for developers seeking faster coding assistance.

How to set up a custom system prompt

How to change hotkeys in Ozeki Voice Keyboard

Customize your keyboard shortcuts to avoid conflicts and match your workflow preferences. This guide walks you through reassigning hotkeys for voice transcription and AI assistant functions via the system tray context menu for maximum efficiency and comfort.

How to change hotkeys in Ozeki Voice Keyboard

How to set up a custom system prompt

You can boost productivity by creating a custom system prompt tailored to your workflow. Ozeki Voice Keyboard allows you to define a system prompt that is sent with every AI assistant request, giving you faster and more relevant responses without having to repeat context each time.

What is a system prompt?

A system prompt is a set of instructions sent to the AI model before your question. It defines the behavior, tone, and output format of the AI assistant so that every response is consistent with your needs. For example, a PHP developer can configure the assistant to always return clean, minimal PHP code examples with expected output, without having to specify this on every request.

Example system prompt for PHP developers

You are a PHP expert assistant whose sole purpose is to provide **simple, clear, 
and useful PHP examples** for any function, feature, or concept the user types.

## Core Behavior
- When the user inputs **only a function name or keyword** 
  (e.g., `array_merge`, `explode`, `PDO`, `foreach`), you must:
  1. Briefly explain what it does in **1–2 short sentences**
  2. Provide a **clean, minimal working example**
  3. Show the **expected output**
  4. Optionally include **1–2 practical use cases**

## Style Rules
- Keep everything **simple, beginner-friendly, and concise**
- Avoid long explanations unless explicitly asked
- Use **modern PHP practices** where relevant
- Prefer **real-world examples** over abstract ones
- Always format code properly using ```php blocks

## Output Structure
Always follow this format:

## Function: <function_name>

**Example:**
```php
<simple PHP example>

Steps to follow

1. Open Ozeki Voice Keyboard and locate the tray icon
2. Open the system prompt editor
3. Enter your system prompt
4. Save the system prompt

How to set up a custom system prompt video

The following video shows how to configure a custom system prompt in Ozeki Voice Keyboard step-by-step. The video covers locating the tray icon, opening the system prompt editor, entering the prompt, and saving the configuration.

Step 1 - Open Ozeki Voice Keyboard and locate the 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 the icon is not visible, click the arrow to expand the hidden tray icons (Figure 1).

Step 2 - Open the system prompt editor

Right-click the tray icon to open the context menu and select System prompt to open the system prompt editor window (Figure 2).

The system prompt editor window will open, displaying a text area where you can enter the instructions that will be sent to the AI model with every request. If a prompt was previously saved, it will be visible here and can be edited or replaced (Figure 3).

Step 3 - Enter your system prompt

Type or paste your system prompt into the text area. The prompt should clearly describe the role and behavior you want the AI assistant to adopt. You can use the PHP developer example from the top of this page as a starting point, or write one that fits your own workflow (Figure 4).

Step 4 - Save the system prompt

Once you have entered your system prompt, click OK to save the configuration. The prompt is now active and will be included with every AI assistant request made (Figure 5).

To sum it up

You have successfully configured a custom system prompt for Ozeki Voice Keyboard. The AI assistant will now use this prompt as context for every request, allowing you to get consistently formatted, relevant responses without repeating instructions. You can update the prompt at any time by returning to the system prompt editor through the tray icon context menu.

How to change hotkeys in Ozeki Voice Keyboard

This guide demonstrates how to change the keyboard shortcuts used by Ozeki Voice Keyboard. You can reassign the default hotkeys for voice transcription and the AI assistant to any key combination that fits your workflow, avoiding conflicts with other applications on your system.

Steps to follow

1. Open Ozeki Voice Keyboard and locate the tray icon
2. Open the keyboard shortcut settings
3. Record a new key combination
4. Save the shortcut settings

How to change hotkeys video

The following video shows how to change the hotkeys in Ozeki Voice Keyboard step-by-step. The video covers locating the tray icon, opening the keyboard shortcut settings, recording a new key combination, and saving the configuration.

Step 1 - Open Ozeki Voice Keyboard and locate the 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 the icon is not visible, click the arrow to expand the hidden tray icons (Figure 1).

Step 2 - Open the keyboard shortcut settings

Right-click the tray icon to open the context menu and select Shortcuts to open the shortcut configuration window (Figure 2).

The keyboard shortcut settings window displays the currently assigned hotkeys for each available action, including voice transcription and the AI assistant. From here you can record new key combinations to replace the defaults (Figure 3).

Step 3 - Record a new key combination

Click the input field under the action you want to reassign then press the key combination you want to use. The window will register the keys you press and display the new combination in the field (Figure 4).

Step 4 - Save the shortcut settings

Once you have recorded your preferred key combinations, click OK to save the configuration. The new hotkeys will take effect immediately (Figure 5).

Conclusion

You have successfully changed the hotkeys in Ozeki Voice Keyboard. The new key combinations are now active and ready to use. You can return to the keyboard shortcut settings at any time through the tray icon context menu to reassign them again if needed.

Ozeki Voice Keyboard Administration

Explore the guides we have created for System Administrators, who are responsible for managing Ozeki Voice Keyboard. The guides include installation, uninstallation instructions and information on how to setup routing through Ozeki AI Gateway.

How to Install Ozeki Voice Keyboard

This guide provides step-by-step instructions for installing Ozeki Voice Keyboard on your Windows computer. It covers the download process, system requirements, and initial setup to get you started with voice input.

How to Install Ozeki Voice Keyboard

How to uninstall Ozeki Voice Keyboard

This tutorial explains the standard uninstallation process for Ozeki Voice Keyboard through Windows settings or control panel, ensuring all components are properly removed.

How to Uninstall Ozeki Voice Keyboard

Manual Uninstallation of Ozeki Voice Keyboard

Learn how to manually remove Ozeki Voice Keyboard from your system using Windows control panel and by deleting remaining files and registry entries for a complete uninstallation.

Manual Uninstallation of Ozeki Voice Keyboard

How to Reinstall Ozeki Voice Keyboard

Follow these instructions to reinstall Ozeki Voice Keyboard, including uninstalling the existing version first, then downloading and installing a fresh copy to resolve issues.

How to Reinstall Ozeki Voice Keyboard

Setup local AI services to serve Ozeki Voice Keyboard

Configure local AI services including Whisper for speech-to-text and LLM backends. Keep all transcriptions and AI processing on your own network infrastructure for complete data privacy and security.

How to setup local AI services for Ozeki Voice Keyboard

How to route Ozeki Voice Keyboard through Ozeki AI Gateway

This guide demonstrates how to connect Ozeki Voice Keyboard to Ozeki AI Gateway, allowing you to route both voice transcription and AI assistant requests through a centralized gateway to a local or remote AI model. This setup is ideal for teams and organizations who operate their own AI infrastructure.

How to route Ozeki Voice Keyboard through Ozeki AI Gateway

How to Install Ozeki Voice Keyboard

This guide demonstrates how to download and install Ozeki Voice Keyboard on Windows. You will learn how to download the ZIP file from the Ozeki website, extract the installer from it, and complete the setup wizard to get the application running on your system.

Steps to follow

1. Navigate to download page
2. Download the installer
3. Locate and extract the folder
4. Run the installer
5. Complete the setup

How to download and install Ozeki Voice Keyboard video

The following video shows how to download and install Ozeki Voice Keyboard step-by-step. The video covers navigating to the download page, extracting the installer, and completing the setup wizard.

Step 1 - Navigate to download page

Open your browser and navigate to the Ozeki Voice Keyboard download page. This page contains the latest version of the installer package available for download (Figure 1).

Step 2 - Download the installer

Download the latest version of the installer to your computer. The file will be saved to your default downloads folder as a compressed ZIP archive (Figure 2).

Step 3 - Locate and extract the folder

Open your Downloads folder and locate the downloaded ZIP file, for example OzKey_1.0.6.zip (Figure 3).

Right-click the ZIP file and select Extract All to unpack its contents. Select a destination folder for the extracted files and confirm the extraction. Once complete, the OzKey installer executable will be available inside the folder (Figure 4).

Step 4 - Run the installer

Open the extracted folder and double-click the OzKey installer executable to launch the setup wizard. If prompted by Windows User Account Control, click Yes to allow the installer to run (Figure 5).

Step 5 - Complete the setup

The OzKey setup wizard will open with a welcome page that briefly explains the installation process. Click Next to proceed with the installation (Figure 6).

You will be presented with the license agreement. Read through the agreement. Click I Agree to proceed if you accept the terms (Figure 7).

Choose the installation directory where Ozeki Voice Keyboard will be installed. The default location is recommended for most users. Click Next to continue (Figure 8).

Select the components you want to install: you can optionally enable Start Menu Shortcut and Desktop Shortcut for easier access to the application after installation. Click Install to proceed (Figure 9).

The installer will copy all necessary files to the selected directory. A progress bar indicates how much of the installation has completed (Figure 10).

Once the installation is complete, the wizard will display a confirmation screen. Click Finish to close the installer. Ozeki Voice Keyboard is now installed and ready to use on your system (Figure 11).

To sum it up

You have successfully downloaded and installed Ozeki Voice Keyboard on your Windows system. The application is now ready to be configured with your preferred voice transcription and AI assistant services. You can check out our How to set up your LLM service in Ozeki Voice Keyboard and How to set up your Voice detection service in Ozeki Voice Keyboard guides on the topics.

Manual Uninstallation of Ozeki Voice Keyboard

This guide demonstrates how to manually remove Ozeki Voice Keyboard from your Windows system. You will learn how to delete all application files, remove the Start Menu entry, clean up the Windows registry, and delete the program folder.

Steps to follow

1. Delete the OzKey AppData folder
2. Remove the Start Menu entry
3. Remove the registry entry
4. Delete the Program Files folder
5. Remove the desktop shortcut

Quick reference paths

# Application data folder
C:\Users\{User}\AppData\Roaming\Ozeki\OzKey

# Start Menu entry
C:\Users\{User}\AppData\Roaming\Microsoft\Windows\Start Menu\Programs\Ozeki\OzKey

# Registry key
HKEY_LOCAL_MACHINE\SOFTWARE\WOW6432Node\Microsoft\Windows\CurrentVersion\Uninstall\OzekiOzKey

# Program Files folder
C:\Program Files\Ozeki\OzKey

How to manually uninstall Ozeki Voice Keyboard video

The following video shows how to manually uninstall Ozeki Voice Keyboard step-by-step. The video covers deleting the application data folder, removing the Start Menu entry, cleaning up the registry, and deleting the remaining program files.

Step 1 - Delete the OzKey AppData folder

Open Windows File Explorer and navigate to the OzKey application data folder. This folder contains user-specific data such as recordings and logs. Replace {User} with your Windows username (Figure 1).

C:\Users\{User}\AppData\Roaming\Ozeki\OzKey

Right-click the OzKey folder and select Delete to remove it (Figure 2).

Step 2 - Remove the Start Menu entry

Navigate to the OzKey Start Menu folder. This folder contains the shortcut that appears in the Windows Start Menu and was created during installation (Figure 3).

C:\Users\{User}\AppData\Roaming\Microsoft\Windows\Start Menu\Programs\Ozeki

Right-click the OzKey shortcut and select Delete to remove it from the Start Menu (Figure 4).

Step 3 - Remove the registry entry

Open the Windows Registry Editor by opening windows search, typing regedit into the search bar, and pressing Enter. The Registry Editor allows you to view and modify low-level Windows system settings (Figure 5).

Navigate to the OzKey uninstall registry key by pasting the following path into the Registry Editor's address bar (Figure 6).

HKEY_LOCAL_MACHINE\SOFTWARE\WOW6432Node\Microsoft\Windows\CurrentVersion\Uninstall\OzekiOzKey

Right-click the OzekiOzKey key in the left panel and select Delete to remove it. Confirm the deletion when prompted. Once this key is removed, Windows will no longer list Ozeki Voice Keyboard as an installed program (Figure 7).

Step 4 - Delete the Program Files folder

Open File Explorer and navigate to the Ozeki folder inside Program Files. This folder contains the application binaries (Figure 8).

C:\Program Files\Ozeki\OzKey

Right-click the OzKey folder and select Delete to remove it (Figure 9).

Step 5 - Remove the desktop shortcut

If a desktop shortcut was created during installation, locate the OzKey icon on your desktop. Right-click the shortcut and select Delete to remove it. This is the final step in the manual uninstallation process (Figure 10).

Final thoughts

You have successfully removed all traces of Ozeki Voice Keyboard from your Windows system. By deleting the application data folder, Start Menu entry, registry key, program files, and desktop shortcut, the application is now fully uninstalled without leaving any residual files or system entries behind.

How to Uninstall Ozeki Voice Keyboard

This guide demonstrates how to uninstall Ozeki Voice Keyboard from your Windows system using the built-in uninstaller. You will learn how to locate the application in the Windows installed apps list and remove it cleanly in just a few steps.

Steps to follow

1. Open the Installed Apps menu
2. Search for OzKey
3. Uninstall Ozeki Voice Keyboard

How to uninstall Ozeki Voice Keyboard video

The following video shows how to uninstall Ozeki Voice Keyboard step-by-step. The video covers opening the installed apps list, finding Ozeki Voice Keyboard, and running the uninstaller to completion.

Step 1 - Open the Installed Apps menu

Click the Windows Search bar in the taskbar and type Installed Apps. Select the Installed Apps system settings result to open the page directly. This page lists all applications currently installed on your system and provides options to modify or remove them (Figure 1).

Step 2 - Search for OzKey

Use the search bar at the top of the Installed Apps page and type OzKey to filter the list. The application will appear in the results once the search completes (Figure 2).

Step 3 - Uninstall Ozeki Voice Keyboard

Click the three-dot menu button on the right side of the OzKey entry to expand the available options. Select Uninstall from the dropdown menu to launch the OzKey uninstaller (Figure 3).

The OzKey uninstaller window will open. Click the Uninstall button to begin removing the application. The uninstaller will automatically remove all application files and entries from your system (Figure 4).

Once the uninstallation is complete, the window will display a confirmation message. Click Close to dismiss the window. Ozeki Voice Keyboard has now been fully removed from your system (Figure 5).

Conclusion

You have successfully uninstalled Ozeki Voice Keyboard from your Windows system using the built-in uninstaller. All application files and system entries have been removed automatically without requiring any manual cleanup.

How to Reinstall Ozeki Voice Keyboard

This guide demonstrates how to reinstall Ozeki Voice Keyboard on Windows. Reinstalling is useful when the application is not functioning correctly or after a system change. The process involves uninstalling the current version and then running the installer to set up a fresh copy of the application.

Steps to follow

1. Uninstall Ozeki Voice Keyboard
2. Reinstall Ozeki Voice Keyboard

How to uninstall Ozeki Voice Keyboard video

The following video shows how to uninstall Ozeki Voice Keyboard in preparation for reinstallation. The video covers locating the application in the installed apps list and running the uninstaller to completion.

Step 1 - Uninstall Ozeki Voice Keyboard

Click the Windows Search bar in the taskbar, type Installed Apps, and open the result. Use the search bar on the Installed Apps page to find OzKey, it will appear in the filtered results once the search completes (Figure 1).

Click the three-dot menu button on the right side of the OzKey entry and select Uninstall from the dropdown menu. This will launch the OzKey uninstaller window (Figure 2).

In the OzKey uninstaller window, click the Uninstall button to begin removing the application. The uninstaller will automatically remove all application files and system entries (Figure 3).

Once the uninstallation is complete, a confirmation message will appear. Click Close to dismiss the window before proceeding with the reinstallation (Figure 4).

Step 2 - Reinstall Ozeki Voice Keyboard

The following video shows how to reinstall Ozeki Voice Keyboard after the previous version has been removed. The video covers running the installer and completing the setup wizard.

Locate the OzKey installer executable - if you no longer have it, download the latest version from the Ozeki Voice Keyboard download page and extract it from the ZIP file. Double-click the installer to launch the setup wizard, and confirm any User Account Control prompt that appears (Figure 5).

The setup wizard welcome screen will appear. Proceed through the installation steps by accepting the license agreement, choosing the installation location, and selecting your preferred components, then click Install to begin (Figure 6).

Once the installation is complete, the wizard will display a confirmation screen. Click Finish to close the installer. Ozeki Voice Keyboard is now freshly installed and ready to be configured (Figure 7).

To sum it up

You have successfully reinstalled Ozeki Voice Keyboard on your Windows system. The application has been cleanly removed and set up from scratch, which resolves most issues caused by corrupted or outdated installation files.

Setup local AI services to serve Ozeki Voice Keyboard

This page provides guides for setting up local AI services including Whisper for speech detection and various LLM backends for Ozeki Voice Keyboard.

Setup AI speech detector

This page provides comprehensive information for setting up Whisper Speech Detector with Ozeki Voice Keyboard across different platforms including Windows, Windows with WSL, and Ubuntu Linux. If you serve speech detection from your own server your transcriptions will not leave your network. Read more: How to use Whisper as a Speech Detector in Ozeki Voice Keyboard

To go directly to platform specific setups, you may follow these links:

• How to set up Whisper Speech Detector on Windows
• How to set up Whisper Speech Detector on Windows WSL
• How to set up Whisper Speech Detector on Ubuntu Linux

Setup LLM backend

This page provides guides on configuring different LLM backends for Ozeki Voice Keyboard, including Ollama on Windows, LLama.cpp on Ubuntu, and vLLM on Ubuntu.If you serve speech detection from your own server your transcriptions will not leave your network. Read more: How to use different LLM backends in Ozeki Voice Keyboard

To go directly to platform specific setups, you may follow these links:

• How to use LLama.cpp as the LLM backend for Ozeki Voice Keyboard on Ubuntu
• How to use Ollama on Windows as the LLM backend for Ozeki Voice Keyboard
• How to use Vllm as the LLM backend for Ozeki Voice Keyboard on Ubuntu

How to use Whisper as a Speech Detector in Ozeki Voice Keyboard

This page provides comprehensive guides for setting up Whisper Speech Detector with Ozeki Voice Keyboard across different platforms including Windows, Windows with WSL, and Ubuntu Linux.

How to set up Whisper Speech Detector on Windows

This tutorial covers installing FFmpeg via winget, creating a Python 3.11 Conda environment, and running the Whisper server with agent-cli. You will configure Ozeki Voice Keyboard to use the local server for speech-to-text transcription by entering the API URL and model name in the Voice settings.

How to set up Whisper Speech Detector on Windows

How to set up Whisper Speech Detector on Windows using WSL

The guide walks through installing WSL with Ubuntu, updating packages, and installing required dependencies including Python, FFmpeg, and NVIDIA CUDA toolkit. You will create a Python virtual environment, install agent-cli with the faster-whisper backend, and start the Whisper server. Finally, configure Ozeki Voice Keyboard to connect to the WSL-hosted Whisper server for offline voice transcription.

How to set up Whisper Speech Detector on Windows WSL

How to set up Whisper Speech Detector on Ubuntu Linux

This guide demonstrates creating a Python 3.12 Conda environment on Ubuntu, installing vLLM with audio support, and starting the Whisper server. The server exposes an OpenAI-compatible endpoint accessible over the network. You will configure Ozeki Voice Keyboard to send audio to the Ubuntu machine for transcription, allowing you to offload speech processing to a dedicated Linux machine on your network.

How to set up Whisper Speech Detector on Ubuntu Linux

How to set up Whisper Speech Detector on Windows

This guide demonstrates how to set up a local Whisper speech recognition server on Windows and connect it to Ozeki Voice Keyboard. You will learn how to install the required dependencies, start the Whisper server using agent-cli, and configure Ozeki Voice Keyboard to use it for speech-to-text transcription.

What is Whisper?

Whisper is an open-source speech recognition model developed by OpenAI. In this setup, it is run locally on your Windows machine using the faster-whisper backend via agent-cli, which exposes an OpenAI-compatible /v1/audio/transcriptions endpoint. This allows Ozeki Voice Keyboard to send recorded audio to the local server and receive transcribed text in response.

Steps to follow

Before proceeding, make sure Anaconda is installed on your system. FFmpeg can be installed via winget, which is built into Windows 10 and 11. The agent-cli package will be installed via pip during the setup process.

1. Open a terminal window
2. Install FFmpeg
3. Set up the Anaconda environment
4. Install agent-cli with faster-whisper
5. Start the Whisper server
6. Connect Whisper to Ozeki Voice Keyboard

Quick reference commands

# Install FFmpeg audio processing library
winget install ffmpeg

# Create a Python 3.11 Conda environment
conda create -n whisper-ai python=3.11 -y

# Activate the environment
conda activate whisper-ai

# Install agent-cli with the faster-whisper backend
pip install "agent-cli[faster-whisper]"

# Start the Whisper server using the small model
agent-cli server whisper --model small

How to set up and run Whisper on Windows video

The following video shows how to set up and run the Whisper speech recognition server on Windows step-by-step. The video covers installing FFmpeg, creating the Conda environment, installing agent-cli, and starting the server.

Step 1 - Open a terminal window

Open a terminal window on your system. All setup commands in this guide are run from the terminal. You can use Windows PowerShell, or the standard Command Prompt (Figure 1).

Step 2 - Install FFmpeg

Install FFmpeg using the winget package manager. FFmpeg is required by the Whisper backend to handle audio file processing before transcription (Figure 2).

winget install ffmpeg

Step 3 - Set up the Anaconda environment

Create a dedicated Conda environment with Python 3.11 for the Whisper server. Using a separate environment keeps its dependencies isolated from other Python projects on your system (Figure 3).

conda create -n whisper-ai python=3.11 -y

Activate the newly created environment. Your terminal prompt will update to show the active environment name (Figure 4).

conda activate whisper-ai

Step 4 - Install agent-cli with faster-whisper

With the environment active, install agent-cli together with the faster-whisper backend using pip. The faster-whisper extra installs all dependencies needed to run the Whisper speech recognition model locally (Figure 5).

pip install "agent-cli[faster-whisper]"

Step 5 - Start the Whisper server

Start the Whisper server using agent-cli with the small model. You can choose between the different model sizes depending on how powerful your computer is (Figure 6).

agent-cli server whisper --model small

On the first run, agent-cli will automatically download and install the Wyoming protocol dependency. Wait for this process to complete before proceeding (Figure 7).

Once the dependency installation finishes, run the server start command again. This is only required on the first run (Figure 8).

agent-cli server whisper --model small

The Whisper server is now running and listening for transcription requests. Keep this terminal open for the duration of your session (Figure 9).

Step 6 - Connect Whisper to Ozeki Voice Keyboard

The following video shows how to connect the Whisper server to Ozeki Voice Keyboard and verify that transcription is working correctly. The video covers copying the API URL, configuring the Voice settings, and confirming the connection through the log viewer.

Copy the API URL from the terminal output. This is the endpoint you will enter in Ozeki Voice Keyboard to point it at the local Whisper server (Figure 10).

http://localhost:10301/v1

Open Ozeki Voice Keyboard and locate its icon in the Windows system tray in the bottom right corner of your taskbar (Figure 11).

Before configuring the Voice settings, enable HTTP logging so you can verify that requests are reaching the Whisper server. Right-click the tray icon and navigate to Logs from the context menu (Figure 12).

In the Logs window, enable HTTP logging and close the window. This will allow you to monitor the requests sent to the Whisper server after configuration (Figure 13).

Right-click the tray icon again and open the Voice settings from the context menu (Figure 14).

Enter the API URL you copied from the terminal, append "/audio/transcriptions" to the end of the URL, specify the model name, and leave the API key field empty since the local server does not require authentication. Click OK to save the settings (Figure 15).

Test the setup by placing your cursor in any input field and using the voice recording hotkey to dictate some text. The audio will be sent to the local Whisper server and the transcription will be pasted into the active field (Figure 16).

Open the Logs window to verify the request. You should see an HTTP request to the /v1/audio/transcriptions endpoint, confirming that Ozeki Voice Keyboard is successfully communicating with the local Whisper server (Figure 17).

To sum it up

You have successfully set up a local Whisper speech recognition server on Windows and connected it to Ozeki Voice Keyboard. The application will now use your local Whisper instance for all voice transcriptions, giving you a fast, private, and fully offline speech-to-text pipeline that does not rely on any external cloud service.

How to set up Whisper Speech Detector on Windows using WSL

This guide demonstrates how to set up a local Whisper speech recognition server on Windows using the Windows Subsystem for Linux (WSL) and connect it to Ozeki Voice Keyboard. You will learn how to install Ubuntu on WSL, set up the required dependencies, start the Whisper server, and configure Ozeki Voice Keyboard to use it for speech-to-text transcription.

What is Whisper?

Whisper is an open-source speech recognition model developed by OpenAI. In this setup, it is run inside a WSL Ubuntu environment using the faster-whisper backend via agent-cli, which exposes an OpenAI-compatible endpoint. This allows Ozeki Voice Keyboard to send recorded audio to the local server and receive transcribed text in response.

Steps to follow

Before proceeding, make sure WSL is enabled on your system. Python, FFmpeg, and pip will be installed inside the WSL Ubuntu environment during the setup process.

1. Open a terminal window
2. Install WSL with Ubuntu
3. Update Ubuntu packages
4. Install required packages
5. Set up the Python virtual environment
6. Install agent-cli with faster-whisper
7. Start the Whisper server
8. Connect Whisper to Ozeki Voice Keyboard

Quick reference commands

# Install WSL with Ubuntu
wsl --install -d Ubuntu

# Update and upgrade Ubuntu packages
sudo apt update && sudo apt upgrade -y

# Install Python, FFmpeg, venv and CUDA toolkit for Nvidia GPUs
sudo apt install python3 python3-pip ffmpeg python3.12-venv nvidia-cuda-toolkit -y

# Create a Python virtual environment
python3 -m venv whisper-env

# Activate the virtual environment
source whisper-env/bin/activate

# Install agent-cli with the faster-whisper backend
pip install "agent-cli[faster-whisper]"

# Start the Whisper server using the small model
agent-cli server whisper --model small

How to set up and run Whisper on Windows WSL video

The following video shows how to set up and run the Whisper speech recognition server on Windows using WSL step-by-step. The video covers installing Ubuntu on WSL, setting up the Python environment, installing agent-cli, and starting the server.

Step 1 - Open a terminal window

Open a terminal window on your Windows system. All setup commands in this guide are run from the terminal (Figure 1).

Step 2 - Install WSL with Ubuntu

Run the following command to install WSL with the Ubuntu distribution. This will download and set up a full Ubuntu Linux environment that runs directly inside Windows without requiring a separate virtual machine (Figure 2).

wsl --install -d Ubuntu

Once the installation completes, you will be prompted to create a Unix user account. Enter a username and password for your Ubuntu environment (Figure 3).

Step 3 - Update Ubuntu packages

Update and upgrade the Ubuntu package list to make sure all system packages are current before installing any dependencies (Figure 4).

sudo apt update && sudo apt upgrade -y

Step 4 - Install required packages

Install Python, pip, FFmpeg, the Python venv module, and the NVIDIA CUDA toolkit in a single command. FFmpeg handles audio processing, venv is needed to create the isolated Python environment, and the CUDA toolkit enables GPU-accelerated transcription if your system has a compatible NVIDIA graphics card (Figure 5).

sudo apt install python3 python3-pip ffmpeg python3.12-venv nvidia-cuda-toolkit -y

Step 5 - Set up the Python virtual environment

Create a dedicated Python virtual environment for the Whisper server. Using a separate environment keeps its dependencies isolated from other Python projects on your system (Figure 6).

python3 -m venv whisper-env

Activate the virtual environment. Your terminal prompt will update to show the active environment name (Figure 7).

source whisper-env/bin/activate

Step 6 - Install agent-cli with faster-whisper

With the virtual environment active, install agent-cli together with the faster-whisper backend using pip. This installs all dependencies needed to run the Whisper speech recognition model locally inside WSL (Figure 8).

pip install "agent-cli[faster-whisper]"

Step 7 - Start the Whisper server

Start the Whisper server using agent-cli with the small model. You can choose between different model sizes depending on how powerful your system is (Figure 9).

agent-cli server whisper --model small

The Whisper server is now running and listening for transcription requests. Keep this terminal open for the duration of your session (Figure 10).

Step 8 - Connect Whisper to Ozeki Voice Keyboard

The following video shows how to connect the WSL Whisper server to Ozeki Voice Keyboard and verify that transcription is working correctly.

Copy the API URL from the terminal output. This is the endpoint you will enter in Ozeki Voice Keyboard to point it at the local Whisper server (Figure 11).

For example: http://localhost:10301/v1

Open Ozeki Voice Keyboard and locate its icon in the Windows system tray in the bottom right corner of your taskbar (Figure 12).

Before configuring the Voice settings, enable HTTP logging so you can verify that requests are reaching the Whisper server. Right-click the tray icon and navigate to Logs from the context menu (Figure 13).

In the Logs window, enable HTTP logging and close the window. This will allow you to monitor the requests sent to the Whisper server after configuration (Figure 14).

Right-click the tray icon again and open the Voice settings from the context menu (Figure 15).

Enter the API URL you copied from the terminal, append "/audio/transcriptions" to the end of the URL and specify the model name. The API key does not matter since the local server does not require authentication. Click OK to save the settings (Figure 16).

Test the setup by placing your cursor in any input field and using the voice recording hotkey to dictate some text. The audio will be sent to the Whisper server running inside WSL and the transcription will be pasted into the active field (Figure 17).

Open the Logs window to verify the request. You should see an HTTP request to the /v1/audio/transcriptions endpoint, confirming that Ozeki Voice Keyboard is successfully communicating with the Whisper server running inside WSL (Figure 18).

Final thoughts

You have successfully set up a local Whisper speech recognition server on Windows using WSL and connected it to Ozeki Voice Keyboard. Running the server inside WSL gives you the flexibility of a Linux environment while staying on Windows, and the fully local setup means your voice data never leaves your machine.

How to set up Whisper Speech Detector on Ubuntu Linux

This guide demonstrates how to set up a Whisper speech recognition server on an Ubuntu machine and connect it to Ozeki Voice Keyboard running on Windows. You will learn how to install the required dependencies, start the Whisper server using vLLM, and configure Ozeki Voice Keyboard to send audio to the Ubuntu machine for transcription over the network.

What is Whisper?

Whisper is an open-source speech recognition model developed by OpenAI. In this setup, it is served on an Ubuntu machine using vLLM, which exposes an OpenAI-compatible endpoint on the network. Ozeki Voice Keyboard, running on a separate Windows machine, sends recorded audio to this endpoint and receives the transcribed text in response.

System architecture

The diagram below illustrates how the Windows machine running Ozeki Voice Keyboard communicates with the Ubuntu machine hosting the Whisper server.

Steps to follow

Before proceeding, make sure Anaconda is installed on your Ubuntu machine. The vllm package will be installed via pip during the setup process.

1. Create and activate the Conda environment
2. Install vLLM
3. Start the Whisper server
4. Connect Whisper to Ozeki Voice Keyboard

Quick reference commands

# Create a Python 3.12 Conda environment
conda create -n whisper python=3.12

# Activate the environment
conda activate whisper

# Install vLLM with audio support
pip install vllm vllm[audio]

# Start the Whisper server
vllm serve openai/whisper-small

# API endpoint (replace with your Ubuntu machine's IP)
http://ubuntu.machine/v1/audio/transcriptions

How to set up Whisper on Ubuntu video

The following video shows how to set up and run the Whisper speech recognition server on Ubuntu step-by-step. The video covers creating the Conda environment, installing vLLM, and starting the server.

Step 1 - Create and activate the Conda environment

Open a terminal on your Ubuntu machine and create a dedicated Conda environment with Python 3.12 for the Whisper server. Using a separate environment keeps its dependencies isolated from other Python projects on your system (Figure 1).

conda create -n whisper python=3.12

Activate the newly created environment. Your terminal prompt will update to show the active environment name (Figure 2).

conda activate whisper

Step 2 - Install vLLM

With the environment active, install vLLM along with its audio support extra using pip. The vllm[audio] extra includes all dependencies needed to serve Whisper as an audio transcription endpoint (Figure 3).

pip install vllm vllm[audio]

Step 3 - Start the Whisper server

Start the Whisper server by running the vLLM serve command with the small model (You can also use more powerful models depending on your hardware configuration). The server will download the model on the first run, which may take a few minutes depending on your connection speed (Figure 4).

vllm serve openai/whisper-small

Once the server has started, it will begin listening for transcription requests on port 8000. Keep this terminal open for the duration of your session. The endpoint is accessible to other machines on your network at http://{your-ip-address}/v1/audio/transcriptions (Figure 5).

Step 4 - Connect Whisper to Ozeki Voice Keyboard

The following video shows how to connect the Ubuntu Whisper server to Ozeki Voice Keyboard on Windows and verify that transcription is working correctly. The video covers locating the tray icon, enabling HTTP logging, configuring the Voice settings, and confirming the connection through the log viewer.

On your Windows machine, open Ozeki Voice Keyboard and locate its icon in the system tray in the bottom right corner of your taskbar (Figure 6).

Before configuring the Voice settings, enable HTTP logging so you can verify that requests are reaching the Ubuntu Whisper server. Right-click the tray icon and navigate to Logs from the context menu (Figure 7).

In the Logs window, enable HTTP logging and close the window. This will allow you to monitor outgoing requests to the Whisper server after configuration (Figure 8).

Right-click the tray icon again and open the Voice settings from the context menu (Figure 9).

Enter the API URL of your Ubuntu machine and specify the model ID. You can leave the API key field empty since the local server does not require authentication. Click OK to save the settings (Figure 10).

http://{ubuntu-machine-ip}:8000/v1/audio/transcriptions

Test the setup by placing your cursor in any input field on the Windows machine and using the voice recording hotkey to dictate some text. The audio will be sent over to the Whisper server on the Ubuntu machine, and the transcription will be pasted into the active field (Figure 11).

Open the Logs window to verify the request. You should see an HTTP request to the Ubuntu machine's /v1/audio/transcriptions endpoint, confirming that Ozeki Voice Keyboard is successfully communicating with the remote Whisper server (Figure 12).

To sum it up

You have successfully set up a Whisper speech recognition server on Ubuntu and connected it to Ozeki Voice Keyboard on Windows. This setup allows you to offload speech processing to a dedicated Linux machine on your network, keeping the Windows machine lightweight while still benefiting from fast and accurate voice transcription.

How to use different LLM backends in Ozeki Voice Keyboard

This page provides guides on configuring different LLM backends for Ozeki Voice Keyboard, including Ollama on Windows, LLama.cpp on Ubuntu, and vLLM on Ubuntu. Each guide covers setup, configuration, and usage of local AI assistants with voice input.

How to use Ollama on Windows as the LLM backend for Ozeki Voice Keyboard

This guide shows how to configure Ollama as the LLM backend for Ozeki Voice Keyboard on Windows. It covers verifying Ollama is running, enabling HTTP logging, configuring LLM settings, using the AI assistant with voice commands, and checking requests in logs. The integration allows voice queries to be processed locally using Ollama's API at localhost:11434.

How to use Ollama on Windows as the LLM backend for Ozeki Voice Keyboard

How to use LLama.cpp as the LLM backend for Ozeki Voice Keyboard on Ubuntu

This tutorial demonstrates building and configuring a LLama.cpp server on Ubuntu as the LLM backend for Ozeki Voice Keyboard. It explains setting up Conda, cloning and building LLama.cpp with CUDA support, downloading the LLM model, starting the server, and connecting it to the voice keyboard for GPU-accelerated inference over the network.

How to use LLama.cpp as the LLM backend for Ozeki Voice Keyboard on Ubuntu

How to use vLLM as the LLM backend for Ozeki Voice Keyboard on Ubuntu

This guide explains how to set up a vLLM server on Ubuntu as the LLM backend for Ozeki Voice Keyboard on Windows. It covers creating a Conda environment, installing vLLM via pip, starting the server with the Qwen model, and connecting it to Ozeki Voice Keyboard. The setup enables GPU-accelerated inference over the network for voice queries.

How to use Vllm as the LLM backend for Ozeki Voice Keyboard on Ubuntu

How to use Ollama on Windows as the LLM backend for Ozeki Voice Keyboard

This guide demonstrates how to configure Ollama as the LLM backend for Ozeki Voice Keyboard on Windows. By integrating a locally running Ollama instance, the AI assistant feature can process voice queries entirely on your machine: your speech is transcribed by the configured voice model, the resulting text is sent to Ollama as a prompt, and the generated response is automatically inserted into the active input field.

How it works

The diagram below illustrates the full pipeline of the AI assistant feature.

Steps to follow

Before proceeding, make sure Ollama is installed on your Windows machine and at least one AI model has been downloaded and is ready to use. You can check out our guide about How to install Ollama

1. Verify Ollama is running
2. Open Ozeki Voice Keyboard and enable logging
3. Configure the LLM settings
4. Ask the AI assistant a question
5. Check the request in logs

How to use Ollama as the LLM backend video

The following video shows how to configure Ollama as the LLM backend for Ozeki Voice Keyboard step-by-step. The video covers configuring the LLM settings, using the AI assistant, and confirming the request in the log viewer.

Step 1 - Verify Ollama is running

Before configuring Ozeki Voice Keyboard, confirm that Ollama is running on your Windows machine and that the AI model you want to use is installed and available. Ollama exposes an OpenAI-compatible API on http://localhost:11434/v1 by default (Figure 1).

Step 2 - Open Ozeki Voice Keyboard and enable logging

Open Ozeki Voice Keyboard and locate its icon in the system tray in the bottom right corner of your taskbar (Figure 2).

Before configuring the LLM settings, enable HTTP logging so you can verify that requests are reaching Ollama after setup. Right-click the tray icon and navigate to Logs from the context menu (Figure 3).

In the Logs window, enable HTTP logging and close the window. Outgoing requests to Ollama will now be recorded and visible in the log viewer (Figure 4).

Step 3 - Configure the LLM settings

Right-click the tray icon and open the LLM settings from the context menu (Figure 5).

Enter the Ollama API URL and specify the model name you want to use. You can leave the API key field empty since a local Ollama instance does not require authentication. Click OK to save the settings (Figure 6).

http://localhost:11434/v1

Step 4 - Ask the AI assistant a question

Place your cursor in any input field where you want the response to appear, then press and hold Ctrl + Space and speak your question into the microphone. Release the keys when you have finished speaking. Your voice will first be transcribed, then the text will be forwarded to Ollama as a prompt (Figure 7).

Once Ollama finishes generating the response, it is automatically pasted into the input field that was active when you started recording. No manual copying or pasting is required (Figure 8).

Step 5 - Check the request in logs

Open the Logs window to confirm that the request was sent correctly. You should see an HTTP request to the Ollama /v1/chat/completions endpoint, confirming that Ozeki Voice Keyboard is successfully communicating with the local Ollama instance (Figure 9).

Conclusion

You have successfully configured Ollama as the LLM backend for Ozeki Voice Keyboard on Windows. The AI assistant is now fully operational: press the hotkey, ask your question by voice, and the response will be generated by your local Ollama model and typed directly into whatever field is currently active on your screen.

How to use LLama.cpp as the LLM backend for Ozeki Voice Keyboard on Ubuntu

This guide demonstrates how to build and configure a LLama.cpp server on Ubuntu as the LLM backend for Ozeki Voice Keyboard on Windows. By running LLama.cpp on a dedicated Ubuntu machine, the AI assistant feature can leverage GPU-accelerated inference over the network: your speech is transcribed by the configured voice model, the resulting text is forwarded to LLama.cpp as a prompt, and the generated response is inserted into the active input field on your Windows machine.

How it works

The diagram below illustrates the full pipeline of the AI assistant feature across the two machines.

Steps to follow

Before proceeding, make sure Anaconda and Git are installed on your Ubuntu machine. A CUDA-compatible NVIDIA GPU is required for GPU-accelerated inference.

1. Set up the Conda environment
2. Clone LLama.cpp
3. Build LLama.cpp with CUDA support
4. Download the LLM model
5. Start the LLama.cpp server
6. Connect LLama.cpp to Ozeki Voice Keyboard

Quick reference commands

# Conda environment
conda create -n qwen35 python=3.12
conda activate qwen35

# Working directory and clone
mkdir qwen35
cd qwen35
git clone https://github.com/ggerganov/llama.cpp
cd llama.cpp

# Create the CUDA-enabled build_llama script
nano build_llama.sh

export PATH=/usr/local/cuda/bin:$PATH
export CUDACXX=/usr/local/cuda/bin/nvcc
export CUDA_HOME=/usr/local/cuda
rm -rf build
cmake -B build \
  -DGGML_CUDA=ON \
  -DCMAKE_CUDA_ARCHITECTURES=86 \
  -DCMAKE_BUILD_TYPE=Release
cmake --build build --config Release -j$(nproc)

# Running the build script
chmod +x build_llama.sh
./build_llama.sh

# Download model
pip install huggingface_hub
hf download bartowski/Qwen_Qwen3.5-9B-GGUF Qwen_Qwen3.5-9B-Q4_K_M.gguf --local-dir .

# Create the server runner script
nano run.sh

./llama.cpp/build/bin/llama-server \
  -m Qwen_Qwen3.5-9B-Q4_K_M.gguf \
  --host 0.0.0.0 \
  --port 8123 \
  --gpu-layers 99 \
  -ngl 99 \
  -c 8192 \
  -fa auto

# Running the script
chmod +x run.sh
./run.sh

How to set up LLama.cpp on Ubuntu video

The following video shows how to build and run the LLama.cpp server on Ubuntu step-by-step. The video covers creating the Conda environment, cloning and building LLama.cpp with CUDA support, downloading the model, and starting the server.

Step 1 - Set up the Conda environment

Open a terminal on your Ubuntu machine and create a dedicated Conda environment with Python 3.12. Using a separate environment keeps LLama.cpp's dependencies isolated from other projects on your system (Figure 1).

conda create -n qwen35 python=3.12

Activate the environment. Your terminal prompt will update to reflect the active environment name (Figure 2).

conda activate qwen35

Create a working directory for this setup and navigate into it (Figure 3).

mkdir qwen35
cd qwen35

Step 2 - Clone LLama.cpp

Clone the LLama.cpp repository from GitHub into the working directory (Figure 4).

git clone https://github.com/ggerganov/llama.cpp

Navigate into the cloned LLama.cpp directory (Figure 5).

cd llama.cpp

Step 3 - Build LLama.cpp with CUDA support

Create a build script using nano. This script sets the required CUDA environment variables and runs the CMake build with GPU support enabled (Figure 6).

nano build_llama.sh

Paste the following build script content into nano, then save and exit (Ctrl+X, then Y, then Enter). The script configures CMake to build with CUDA enabled and targets CUDA architecture 86, which corresponds to NVIDIA Ampere GPUs (Figure 7).

export PATH=/usr/local/cuda/bin:$PATH
export CUDACXX=/usr/local/cuda/bin/nvcc
export CUDA_HOME=/usr/local/cuda

rm -rf build
cmake -B build \
  -DGGML_CUDA=ON \
  -DCMAKE_CUDA_ARCHITECTURES=86 \
  -DCMAKE_BUILD_TYPE=Release

cmake --build build --config Release -j$(nproc)

Make the build script executable (Figure 8).

chmod +x build_llama.sh

Run the build script. The compilation process may take several minutes depending on your hardware. Once complete, the llama-server binary will be available in the build/bin directory (Figure 9).

./build_llama.sh

Step 4 - Download the LLM model

Navigate back to the working directory and install the huggingface_hub package, which provides the command-line tool used to download the model (Figure 10).

cd ..
pip install huggingface_hub

Download the quantized Qwen 3.5 9B model in GGUF format from Hugging Face. The Q4_K_M quantization offers a good balance between model quality and memory usage (Figure 11).

hf download bartowski/Qwen_Qwen3.5-9B-GGUF Qwen_Qwen3.5-9B-Q4_K_M.gguf --local-dir .

Step 5 - Start the LLama.cpp server

Create a runner script using nano to avoid retyping the server command on each launch (Figure 12).

nano run.sh

Paste the server launch command into the script, then save and exit. The server is configured to listen on all network interfaces on port 8123, load all layers onto the GPU, use a context size of 8192 tokens, and enable flash attention (Figure 13).

./llama.cpp/build/bin/llama-server \
  -m Qwen_Qwen3.5-9B-Q4_K_M.gguf \
  --host 0.0.0.0 \
  --port 8123 \
  --gpu-layers 99 \
  -ngl 99 \
  -c 8192 \
  -fa auto

Make the runner script executable (Figure 14).

chmod +x run.sh

Run the script to start the LLama.cpp server. Keep this terminal open for the duration of your session (Figure 15).

./run.sh

The LLama.cpp server is now running and listening for requests on port 8123. It is accessible to other machines on your local network at http://{your-ip-address}:8123/v1 (Figure 16).

Step 6 - Connect LLama.cpp to Ozeki Voice Keyboard

The following video shows how to connect the Ubuntu LLama.cpp server to Ozeki Voice Keyboard on Windows and verify that the AI assistant is working correctly. The video covers locating the tray icon, enabling HTTP logging, configuring the LLM settings, and confirming the connection through the log viewer.

Open Ozeki Voice Keyboard and locate its icon in the system tray in the bottom right corner of your taskbar (Figure 17).

Before configuring the LLM settings, enable HTTP logging so you can verify that requests are reaching the Ubuntu server. Right-click the tray icon and navigate to Logs from the context menu (Figure 18).

Enable HTTP logging and close the window. Outgoing requests to the LLama.cpp server will now be recorded and visible in the log viewer (Figure 19).

Right-click the tray icon again and open the LLM settings from the context menu (Figure 20).

Enter the API URL of the Ubuntu machine and specify the model name. You can leave the API key field empty since LLama.cpp does not require authentication by default. Click OK to save the settings (Figure 21).

http://{ubuntu-machine-ip}:8123/v1

To test the AI assistant, place your cursor in any input field, then press and hold Ctrl + Space and speak your question into the microphone. Once you release the keys, the recording is transcribed and the resulting text is forwarded to the LLama.cpp server on the Ubuntu machine as a prompt (Figure 22).

Open the Logs window to verify the request. You should see an HTTP request to the LLama.cpp server's /v1/chat/completions endpoint on the Ubuntu machine, confirming that Ozeki Voice Keyboard is successfully communicating with the remote LLM backend (Figure 23).

To sum it up

You have successfully built and configured a LLama.cpp server on Ubuntu and connected it to Ozeki Voice Keyboard on Windows. The AI assistant will now use your Ubuntu machine's GPU to generate responses, giving you a high-performance, fully local LLM backend that operates entirely within your own network without relying on any external cloud service.

How to use vLLM as the LLM backend for Ozeki Voice Keyboard on Ubuntu

This guide demonstrates how to configure a vLLM server on Ubuntu as the LLM backend for Ozeki Voice Keyboard on Windows. By running vLLM on a dedicated Ubuntu machine, the AI assistant feature can leverage GPU-accelerated inference over the network: your speech is transcribed by the configured voice model, the resulting text is forwarded to vLLM as a prompt, and the generated response is automatically inserted into the active input field on your Windows machine.

How it works

The diagram below illustrates the full pipeline of the AI assistant feature across the two machines.

Steps to follow

Before proceeding, make sure Anaconda is installed on your Ubuntu machine. A CUDA-compatible NVIDIA GPU is required for GPU-accelerated inference. The vllm package will be installed via pip during the setup process.

1. Set up the Conda environment
2. Install vLLM
3. Start the vLLM server
4. Connect vLLM to Ozeki Voice Keyboard

Quick reference commands

# Conda environment
conda create -n vllm python=3.12
conda activate vllm

# Install vLLM
pip install vllm

# Start the vLLM server
vllm serve Qwen/Qwen3.5-9B \
  --enforce-eager \
  --max-num-seqs 1 \
  --max-model-len 8192 \
  --gpu-memory-utilization 0.95

How to set up vLLM on Ubuntu video

The following video shows how to set up and run the vLLM server on Ubuntu step-by-step. The video covers creating the Conda environment, installing vLLM, and starting the server.

Step 1 - Set up the Conda environment

Open a terminal on your Ubuntu machine and create a dedicated Conda environment with Python 3.12. Using a separate environment keeps vLLM's dependencies isolated from other projects on your system (Figure 1).

conda create -n vllm python=3.12

Activate the environment. Your terminal prompt will update to reflect the active environment name (Figure 2).

conda activate vllm

Step 2 - Install vLLM

With the environment active, install vLLM using pip. vLLM will automatically download all required dependencies for serving large language models with GPU acceleration (Figure 3).

pip install vllm

Step 3 - Start the vLLM server

Start the vLLM server with the Qwen 3.5 9B model. On the first run, vLLM will automatically download the model from Hugging Face, which may take several minutes depending on your connection speed. The server is configured to use eager execution, limit concurrent sequences to 1, cap the context length at 8192 tokens, and utilize 95% of available GPU memory (Figure 4).

vllm serve Qwen/Qwen3.5-9B \
  --enforce-eager \
  --max-num-seqs 1 \
  --max-model-len 8192 \
  --gpu-memory-utilization 0.95

The vLLM server is now running and listening for requests on port 8000. Keep this terminal open for the duration of your session. The endpoint is accessible to other machines on your local network at http://{your-ubuntu-ip}:8000/v1 (Figure 5).

Step 4 - Connect vLLM to Ozeki Voice Keyboard

The following video shows how to connect the Ubuntu vLLM server to Ozeki Voice Keyboard on Windows and verify that the AI assistant is working correctly. The video covers locating the tray icon, enabling HTTP logging, configuring the LLM settings, and confirming the connection through the log viewer.

On your Windows machine, open Ozeki Voice Keyboard and locate its icon in the system tray in the bottom right corner of your taskbar (Figure 6).

Before configuring the LLM settings, enable HTTP logging so you can verify that requests are reaching the Ubuntu server. Right-click the tray icon and navigate to Logs from the context menu (Figure 7).

Enable HTTP logging and close the window. Outgoing requests to the vLLM server will now be recorded and visible in the log viewer (Figure 8).

Right-click the tray icon again and open the LLM settings from the context menu (Figure 9).

Enter the API URL of the Ubuntu machine and specify the model name. You can leave the API key field empty since vLLM does not require authentication by default. Click OK to save the settings (Figure 10).

http://{ubuntu-machine-ip}:8000/v1

To test the AI assistant, place your cursor in any input field, then press and hold Ctrl + Space and speak your question into the microphone. Once you release the keys, the recording is transcribed and the resulting text is forwarded to the vLLM server on the Ubuntu machine as a prompt (Figure 11).

Open the Logs window to verify the request. You should see an HTTP request to the vLLM server's /v1/chat/completions endpoint on the Ubuntu machine, confirming that Ozeki Voice Keyboard is successfully communicating with the remote LLM backend (Figure 12).

Conclusion

You have successfully configured a vLLM server on Ubuntu and connected it to Ozeki Voice Keyboard on Windows. The AI assistant will now use your Ubuntu machine's GPU to generate responses, giving you a high-performance, fully local LLM backend that operates entirely within your own network without relying on any external cloud service.

How to use Ozeki Voice Keyboard through Ozeki AI Gateway

This guide demonstrates how to connect Ozeki Voice Keyboard to Ozeki AI Gateway, allowing you to route both voice transcription and AI assistant requests through a centralized gateway. This setup is ideal for teams and organizations that want to manage API access, monitor usage, and control which AI models are available to users from a single point.

How it works

The diagram below illustrates the system architecture.

Steps to follow

1. Prerequisites
2. Open Ozeki Voice Keyboard
3. Configure Voice settings
4. Configure LLM settings
5. Test the AI assistant
6. Verify requests in logs

How to use Ozeki Voice Keyboard through Ozeki AI Gateway video

The following video shows how to connect Ozeki Voice Keyboard to Ozeki AI Gateway step-by-step. The video covers verifying the gateway prerequisites, configuring both the Voice and LLM settings on the client, and confirming that requests are routed correctly through the gateway.

Step 1 - Prerequisites

We assume Ozeki AI Gateway is already installed on your system. You can install it on Linux, Windows or Mac.

Providers

Open the Ozeki AI Gateway web interface and navigate to the Providers page. Confirm that two providers are registered: one configured with your Whisper endpoint for speech-to-text transcription, and one configured with your LLM endpoint for the AI assistant (Figure 1).

If you have not set up a provider yet, check out our How to connect to an AI service provider guide.

User account

Navigate to the AI Users page and confirm that a user account exists for the Ozeki Voice Keyboard clients. This user account acts as the identity under which all requests from the client machines will be authenticated and tracked by the gateway (Figure 2).

If you haven't created an AI user account yet, check out our How to create a user account guide.

API keys

Open the user account's API keys page. Two API keys must be present: one that will be used to authenticate voice transcription requests, and one for LLM requests. Having separate keys for each service makes it easier to monitor and control access independently (Figure 3).

Check out our How to create API keys for your users guide if you don't know how to create API keys.

Routes

Navigate to the Routes page and confirm that two routes are configured: one connecting the user to the Whisper provider, and one connecting the user to the LLM provider. Routes define which users are permitted to send requests to which providers, and which models they are allowed to use (Figure 4).

If you haven't configured a route yet, you can find instructions in our How to route AI API requests guide.

Step 2 - Open Ozeki Voice Keyboard

On your Windows machine, open Ozeki Voice Keyboard and locate its icon in the system tray in the bottom right corner of your taskbar (Figure 5).

Step 3 - Configure Voice settings

Right-click the tray icon and open the Voice settings from the context menu (Figure 6).

Enter the Ozeki AI Gateway URL as the API endpoint, specify the Whisper model name, and paste the API key you generated for the user account. The gateway will receive the audio request and forward it to the configured Whisper provider. Click OK to save the settings (Figure 7).

http://localhost/v1/audio/transcriptions

Step 4 - Configure LLM settings

Right-click the tray icon again and open the LLM settings from the context menu (Figure 8).

Enter the Ozeki AI Gateway URL in the same way as the Voice settings, specify the LLM model name, and paste the API key. The gateway will route AI assistant requests to the configured LLM provider. Click OK to save the settings (Figure 9).

http://localhost/v1

Step 5 - Test the AI assistant

To test the AI assistant, place your cursor in any input field, then press and hold Ctrl + Space and speak your question into the microphone. Once you release the keys, the gateway transcribes the recording via the Whisper provider and forwards the resulting text to the LLM provider as a prompt (Figure 10).

Once the LLM finishes generating the response, it is automatically pasted into the active input field (Figure 11).

Step 6 - Verify requests in logs

Right-click the tray icon and navigate to Logs from the context menu to open the log viewer (Figure 12).

In the log viewer, you should see outgoing HTTP requests directed at the Ozeki AI Gateway endpoint, one to /v1/audio/transcriptions for the voice transcription and one to /v1/chat/completions for the LLM response (Figure 13).

Final thoughts

You have successfully configured Ozeki Voice Keyboard to route both voice transcription and AI assistant requests through Ozeki AI Gateway. This setup gives you centralized control over all AI traffic from your client machines. You can monitor usage, manage API keys, swap out providers, and enforce access policies from a single location without making any changes to the individual Windows machines.

References

[1]	Introduction to Ozeki Voice https://ozekivoice.com/p_9347-introduction-to-ozeki-voice.html
[2]	#step-1
[3]	Screenshots of Ozeki Voice Keyboard https://ozekivoice.com/p_469-screenshots-of-ozeki-voice-keyboard.html
[4]	Feature list of Ozeki Voice Keyboard https://ozekivoice.com/p_470-feature-list-of-ozeki-voice-keyboard.html
[5]	Technical Datasheet https://ozekivoice.com/p_471-technical-datasheet.html
[6]	System requirements of Ozeki Voice Keyboard https://ozekivoice.com/p_9349-system-requirements-of-ozeki-voice-keyboard.html
[7]	Ozeki Voice Keyboard Screenshots https://ozekivoice.com/p_9350-ozeki-voice-keyboard-screenshots.html
[8]	Ozeki Voice Keyboard Features https://ozekivoice.com/p_9351-ozeki-voice-keyboard-features.html
[9]	Ozeki Voice Keyboard Manual https://ozekivoice.com/p_9322-ozeki-voice-keyboard-manual.html
[10]	How to select the Microphone in Ozeki Voice Keyboard https://ozekivoice.com/p_9323-how-to-select-the-microphone-in-ozeki-voice-keyboard.html
[11]	How to set up your Voice detection service in Ozeki Voice Keyboard https://ozekivoice.com/p_9325-how-to-set-up-your-voice-detection-service-in-ozeki-voice-keyboard.html
[12]	How to use Ollama on Windows as the LLM backend for Ozeki Voice Keyboard https://ozekivoice.com/p_9336-how-to-use-ollama-on-windows-as-the-llm-backend-for-ozeki-voice-keyboard.html#step-4
[13]	How to set up your LLM service in Ozeki Voice Keyboard https://ozekivoice.com/p_9324-how-to-set-up-your-llm-service-in-ozeki-voice-keyboard.html
[14]	How to set up a custom system prompt https://ozekivoice.com/p_1113-how-to-set-up-a-custom-system-prompt.html
[15]	How to change hotkeys in Ozeki Voice Keyboard https://ozekivoice.com/p_9344-how-to-change-hotkeys-in-ozeki-voice-keyboard.html
[16]	How to route Ozeki Voice Keyboard through Ozeki AI Gateway https://ozekivoice.com/p_9339-how-to-route-ozeki-voice-keyboard-through-ozeki-ai-gateway.html
[17]	Ozeki Voice Keyboard Datasheet https://ozekivoice.com/p_9352-ozeki-voice-keyboard-datasheet.html
[18]	ozekivoice.com https://ozekivoice.com/
[19]	User guide for Ozeki Voice Keyboard https://ozekivoice.com/p_9348-user-guide-for-ozeki-voice-keyboard.html
[20]	Ozeki Voice Keyboard for Business https://ozekivoice.com/p_9340-ozeki-voice-keyboard-for-business.html
[21]	How to improve productivity with Ozeki Voice Keyboard https://ozekivoice.com/p_9343-how-to-improve-productivity-with-ozeki-voice-keyboard.html
[22]	#step-2
[23]	#step-3
[24]	#step-4
[25]	Support https://ozeki-sms-gateway.com/p_428-support.html
[26]	Administrative guide for Ozeki Voice Keyboard https://ozekivoice.com/p_9331-administrative-guide-for-ozeki-voice-keyboard.html
[27]	How to Install Ozeki Voice Keyboard https://ozekivoice.com/p_9334-how-to-install-ozeki-voice-keyboard.html
[28]	How to Uninstall Ozeki Voice Keyboard https://ozekivoice.com/p_9332-how-to-uninstall-ozeki-voice-keyboard.html
[29]	Manual Uninstallation of Ozeki Voice Keyboard https://ozekivoice.com/p_9330-manual-uninstallation-of-ozeki-voice-keyboard.html
[30]	How to Reinstall Ozeki Voice Keyboard https://ozekivoice.com/p_9333-how-to-reinstall-ozeki-voice-keyboard.html
[31]	How to setup local AI services for Ozeki Voice Keyboard https://ozekivoice.com/p_9342-how-to-setup-local-ai-services-for-ozeki-voice-keyboard.html
[32]	#step-5
[33]	Download Ozeki Voice Keyboard http://ozeki-ai-gateway.com/p_9341-download-ozeki-voice-keyboard.html
[34]	Download Ozeki Voice Keyboard https://ozekivoice.com/p_9341-download-ozeki-voice-keyboard.html
[35]	How to use Whisper as a Speech Detector in Ozeki Voice Keyboard https://ozekivoice.com/p_9326-how-to-use-whisper-as-a-speech-detector-in-ozeki-voice-keyboard.html
[36]	How to set up Whisper Speech Detector on Windows https://ozekivoice.com/p_9327-how-to-set-up-whisper-speech-detector-on-windows.html
[37]	How to set up Whisper Speech Detector on Windows WSL https://ozekivoice.com/p_9328-how-to-set-up-whisper-speech-detector-on-windows-wsl.html
[38]	How to set up Whisper Speech Detector on Ubuntu Linux https://ozekivoice.com/p_9329-how-to-set-up-whisper-speech-detector-on-ubuntu-linux.html
[39]	How to use different LLM backends in Ozeki Voice Keyboard https://ozekivoice.com/p_9335-how-to-use-different-llm-backends-in-ozeki-voice-keyboard.html
[40]	How to use LLama.cpp as the LLM backend for Ozeki Voice Keyboard on Ubuntu https://ozekivoice.com/p_9337-how-to-use-llama.cpp-as-the-llm-backend-for-ozeki-voice-keyboard-on-ubuntu.html
[41]	How to use Ollama on Windows as the LLM backend for Ozeki Voice Keyboard https://ozekivoice.com/p_9336-how-to-use-ollama-on-windows-as-the-llm-backend-for-ozeki-voice-keyboard.html
[42]	How to use Vllm as the LLM backend for Ozeki Voice Keyboard on Ubuntu https://ozekivoice.com/p_9338-how-to-use-vllm-as-the-llm-backend-for-ozeki-voice-keyboard-on-ubuntu.html
[43]	How to setup Anaconda for Python on Windows https://ozeki-ai-gateway.com/p_9131-how-to-setup-anaconda-for-python-on-windows.html
[44]	learn.microsoft.com https://learn.microsoft.com/en-us/windows/package-manager/winget/
[45]	How to install Python on Windows https://ozeki-ai-gateway.com/p_9309-how-to-install-python-on-windows.html
[46]	#step-6
[47]	learn.microsoft.com https://learn.microsoft.com/en-us/windows/wsl/install
[48]	#step-7
[49]	#step-8
[50]	How to setup Anaconda for Python on Linux https://ozeki-ai-gateway.com/p_9133-how-to-setup-anaconda-for-python-on-linux.html
[51]	How to connect Ozeki AI Gateway to Ollama https://ozeki-ai-gateway.com/p_9140-how-to-connect-ozeki-ai-gateway-to-ollama.html
[52]	git-scm.com https://git-scm.com/
[53]	How to install Ozeki AI Gateway on Linux https://ozeki-ai-gateway.com/p_3184-how-to-install-ozeki-ai-gateway-on-linux.html
[54]	How to install Ozeki AI Gateway on Windows https://ozeki-ai-gateway.com/p_2052-how-to-install-ozeki-ai-gateway-on-windows.html
[55]	Install Mac using brew https://ozeki-ai-gateway.com/p_2438-install-mac-using-brew.html
[56]	How to connect to an AI service provider https://ozeki-ai-gateway.com/p_3145-how-to-connect-to-an-ai-service-provider.html
[57]	How to create a user account https://ozeki-ai-gateway.com/p_2301-how-to-create-a-user-account.html
[58]	How to create API keys for your users https://ozeki-ai-gateway.com/p_1999-how-to-create-api-keys-for-your-users.html
[59]	How to route AI API requests https://ozeki-ai-gateway.com/p_2303-how-to-route-ai-api-requests.html