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.
